# Shreyas Jagannath
> Senior Applied AI Engineer · Agentic Systems, Developer Tooling, Forward Deployed
> Senior Applied AI Engineer in demand across London and EU AI teams for production agentic systems and developer tooling.

Shreyas Jagannath is a London-based Senior Applied AI Engineer with 8+ years of software experience, currently a Senior AI Engineer at Lendable. He builds production agentic systems and developer tooling, and is the author of Nexus-MCP, an open-source code-intelligence server for AI coding agents published on PyPI. At Klyft he cut LLM token costs 10x and agent execution time 3x (60s → 20s).

Email: shreyasjag@hotmail.com · London, UK · https://shreyasjagannath.com

## Why this candidate
- **8+ years building software; Senior AI Engineer at Lendable.** Lendable Operations Ltd, Jul 2026 — Present. Earlier: CTO of AIMAGE (team of 10) and founding engineer at Klyft, Scan and Sew and Move By Vision.
- **Open-source author of Nexus-MCP.** Hybrid code-intelligence server for AI coding agents: 70–90% token reduction on code lookups, 461 tests, published on PyPI (pip install nexus-mcp-ci) and listed on the Glama MCP marketplace. (https://github.com/jaggernaut007/Nexus-MCP)
- **Production outcomes with numbers.** 10x lower LLM token costs, 3x faster agent execution (60s → 20s) and 100% uptime across GCP deployments at Klyft; 55% lower generation latency (15s → 7s) at Move By Vision.
- **Live product: Protash.** Describe a business intent, get a deployed prototype back in under 5 minutes. (https://protash.shreyasjagannath.com)
- **Conference speaker.** Delivered a workshop at ODSC (Open Data Science Conference) on enterprise AI and deep learning to 100+ professionals.
- **Recognition and research.** 5 awards, including AI Hackathon Winner; peer-reviewed journal paper on machine learning for robotic path planning.
- **Credentials.** MSc Artificial Intelligence (Distinction), University of Surrey; 6 certifications, 4 of them from Anthropic (Claude Code, Model Context Protocol, Agent Skills, Claude API).

## Experience
### Senior AI Engineer at Lendable Operations Ltd (Jul 2026 — Present)
- Context: Internal Engineering Teams (Cross-Org)
- Problem: Engineering data was scattered across incident.io, Jira, Datadog and GitHub with no governed place to model it, and no unified view of how developer tooling was actually being used across the delivery lifecycle.
- Architecture: GitHub, Jira, Claude, and Codex telemetry pipelines feeding the AI Hub dashboard; incident.io, Jira, Datadog, and GitHub data modelled in Snowflake for governed stakeholder access; a company-level engineering cycle-time model attributing each PR to a team by backtracking historical contribution share, with a manager-facing deny-list correction loop; four reusable skills replacing the manual investigation behind every new feature spec; deployment on Terraform/Terragrunt, GitHub Actions CI/CD, and Argo CD, including Okta SCIM/OIDC authentication and admin/user group setup.
- Outcome: Shipped on the organisation's Terraform/Terragrunt, GitHub Actions CI/CD and Argo CD deployment stack, and set up Okta SCIM/OIDC authentication with admin/user group management for the tooling I built. Modelled incident.io, Jira, Datadog and GitHub API data into governed, OKR-level Snowflake metrics leadership could act on. Built the AI Hub on top of it, a full-stack engineering dashboard unifying GitHub, Jira, Claude and Codex telemetry into one view, and cut developer workflow times by up to 10% by instrumenting and optimising the organisation's agent skills, with automated ticket-to-skill detection surfacing the right skill against incoming work. Built a company-level engineering cycle-time model: since the team ledger only reflected current membership, not history, each PR is attributed to a team by backtracking historical contribution share, with a manager-facing deny-list that reassigns mis-attributed contributors automatically — a correction loop instead of a manual audit. Also turned the repeat manual investigation behind every new feature spec — tracing problem depth, mapping affected data points, checking downstream impact, quantifying business case — into four reusable skills, collapsing a multi-round process into a single invocation without losing rigor.

### Founding AI Engineer at Klyft Technologies (Sep 2025 — Nov 2025)
- Context: Health & Wellbeing Coaching Platform
- Problem: Serving multi-agent LLM responses reliably was cost-prohibitive at scale. Needed safe, low-latency, context-rich outputs for a coaching platform spanning workout calibration, nutrition guidance, and mental wellbeing features.
- Architecture: Python, Google ADK, OpenAI & Gemini APIs on Vertex AI, RAG guardrails, scalable GCP infrastructure.
- Outcome: Achieved a 10x reduction in LLM token costs through prompt optimisation and caching, improved agent efficiency 3x (60s to 20s) on the core workout calibration feature — which drove early user adoption — maintained 100% pilot uptime, and delivered 100% safe guardrailed outputs.

### Founding Engineer (Pro Bono) at Move By Vision (Dec 2025 — May 2026)
- Context: Healthtech Platform
- Problem: Inherited a failing Flutter + GCP platform in critical-failure alpha phase with severe latency and crashing issues, compounded by strict compliance requirements in healthcare.
- Architecture: Flutter, Vertex AI integrations with a guard-railing and validation layer, GCP.
- Outcome: Eliminated 100% of AI crash failures, cut generation latency by 55% (15s to 7s) through optimised execution flows, and conducted a full GDPR/AI Act compliance audit to make the system releasable.

### Founding Engineer (Founding Team) at Scan and Sew Inc. (Oct 2024 — Aug 2025)
- Context: 3D Product Designers & Manufacturers
- Problem: Designers lacked a unified way to intuitively search past design libraries and required a spatial CAD 2D-to-3D workflow connected to supply chain operations.
- Architecture: OpenAI LLM/VLM APIs, RAG, Gaussian Splatting (PyTorch3D evaluation), ReactJS, AWS Lambda, GraphQL, DynamoDB.
- Outcome: Shipped a Designer AI Assistant (RAG over docs) and a real-time manufacturing tracking platform. Evaluated custom 3DGS vs APIs and made the strategic call to integrate an API, saving months of dev time.

### Chief Technology Officer at AIMAGE Technologies (Jan 2020 — Aug 2023)
- Context: Enterprise Retailers
- Problem: Retailers losing customers because online platforms lacked an intuitive way to visually try-on items and search through massive catalogs.
- Architecture: Custom vectoriser model and custom graph-based vector database for visual search (feature vectors as nodes, ontology relationships as edges) combining similarity search with graph traversal for relationship-aware queries across catalogs of thousands of products; virtual try-on engine (OpenCV, PyTorch, Unity3D); production deployment on AWS (Lambda, ECS, Neptune, DynamoDB, S3, Kinesis) with GraphQL APIs.
- Outcome: Delivered both platforms to production with full infrastructure ownership, live on a retail client's storefront to lift conversion through visual search. Founded the company and grew the team to 10 across engineering, product, and design over 3.5 years, setting code-review and architecture standards.

### Software Consultant (Part-time) at Mage Ventures Pvt. Ltd. (Oct 2019 — Mar 2021)
- Context: PhonePe (Walmart-owned), Grocery Retail Client
- Problem: Needed a secure cross-platform payment gateway and an AI-powered automated checkout solution for retail environments.
- Architecture: Node.js, React, AWS EC2, TensorFlow, FastAPI, Computer Vision.
- Outcome: Implemented a secure cross-platform payment gateway for Walmart-owned PhonePe across multiple client apps, and built an AI-powered automated grocery checkout engine using computer vision (image segmentation) for a product company.

### AI Consultant (Founding Team) at Cellstrat Inc. (Oct 2018 — Oct 2020)
- Context: TVS Motors, Target, Airbus, Volvo
- Problem: Bridging theoretical AI capabilities and what enterprise organizations can actually absorb and use in a real context.
- Architecture: PyTorch, TensorFlow, Keras, Python, Docker, AWS.
- Outcome: Consulted on AI/ML initiatives for enterprise clients, designing and implementing models in PyTorch, TensorFlow, Keras, and Python, containerised with Docker and deployed on AWS for their digital transformation journey. Delivered a workshop at ODSC (Open Data Science Conference) on implementing AI and deep learning solutions in enterprise environments, training 100+ professionals.

### Full Stack Engineer (Founding Team) at EndGate Global (Jul 2017 — Jul 2018)
- Context: High-volume food delivery services
- Problem: Needed a scalable automation platform for processing and delivering food orders in bulk.
- Architecture: Java, Spring, Hibernate, MySQL, JavaScript.
- Outcome: Developed full-stack food delivery workflows that real businesses depend on, establishing fundamental production software engineering skills.

### AI Researcher Intern at ISRO (Nov 2016 — Apr 2017)
- Context: Chandrayaan Moon Rover Mission
- Problem: Making a rover navigate a lunar environment using a single camera. Solving for geometric uncertainty and edge cases where failure has massive real-world consequences.
- Architecture: Computer Vision algorithms, Mono Vision Depth Detection.
- Outcome: Advanced the perception capabilities of the rover, learning the discipline of high-stakes, fault-intolerant research.

## Skills
### Languages & Frameworks
Python, TypeScript, FastAPI, React, Next.js, Node.js, GraphQL, REST APIs, Flutter
### Cloud & Infrastructure
GCP (Vertex AI, Gemini, Cloud Run, Cloud Build, Secret Manager, Pub/Sub, BigQuery), AWS (Lambda, ECS, S3, Kinesis, DynamoDB, Neptune), Docker, Terraform / Terragrunt, Argo CD, GitHub Actions CI/CD
### Data & Storage
PostgreSQL (Neon, Supabase), Snowflake, BigQuery, DynamoDB, Neo4j, LanceDB, ChromaDB, Pinecone
### AI & LLM Systems
Multi-Agent Orchestration, RAG, MCP (Model Context Protocol), Knowledge Graphs, Evaluations & Guardrails, Prompt Engineering, LLM Cost Optimisation, Hybrid Search / Reciprocal Rank Fusion, LangGraph, LangChain, LlamaIndex, Google ADK, OpenAI, Gemini & DeepSeek APIs, Severity-Based Model Routing, Claude Code
### Developer Tooling & Productivity
MCP Servers & Code Intelligence, AI Coding Agent Tooling, AI Adoption Telemetry, Developer-Productivity Metrics, Workflow Analysis, Agent Skill Instrumentation & Optimisation, GitHub/Jira Data Pipelines, Metrics Dashboards, Claude Code & Cline Custom Harness (skills, agents, hooks, workflows)
### AI / ML
NLP, Computer Vision, Gaussian Splatting, PyTorch, TensorFlow, ONNX Runtime, Hugging Face
### Reliability & Delivery
Evaluation-Driven Development (DeepEval), Fail-Closed CI Gates, Observability (Datadog), Audit Trails & Compliance Registers, Human-in-the-Loop Safety Checks
### Platform Evaluation & Cost
Comparative Hyperscaler Evaluation (Vertex AI vs AWS Bedrock vs Azure ML), Model Suitability, Latency & Cost-Per-Run Analysis, AI Cost Optimisation (Token Reduction, Caching, Model Routing), GDPR & EU AI Act Audit and Remediation

## Projects
### Nexus-MCP: Hybrid Code Intelligence Server (Mar 2026)
Built to unblock a client engagement: a large, undocumented Flutter codebase that AI agents could not navigate reliably. Combines vector search, BM25 and structural code graph analysis for 70–90% token reduction on code lookups, so agents could ship features and fixes against unfamiliar code. Published on PyPI (nexus-mcp-ci) and listed on the Glama MCP marketplace. 15 tools in one local server, tree-sitter parsing across 25+ languages, under 350MB RAM, no cloud dependency and no API keys.
Tags: MCP, ONNX Runtime, LanceDB, rustworkx, tree-sitter, Python
Website: https://pypi.org/project/nexus-mcp-ci/
GitHub: https://github.com/jaggernaut007/Nexus-MCP
- Problem: AI coding agents waste 70–90% of their token budget reading irrelevant code — grepping for a function, reading entire files, repeating for every dependency. Existing code intelligence tools are fragmented across separate servers, each consuming 500 MB+ RAM.
- Approach: Built a single MCP server consolidating two predecessor projects. Dual parsing (tree-sitter for symbol extraction, ast-grep for structural graph) feeds three search engines fused with Reciprocal Rank Fusion (vector 0.5 + BM25 0.3 + graph 0.2). Replaced PyTorch with ONNX Runtime (~50 MB vs ~500 MB), used LanceDB with mmap for disk-backed vectors, and added FlashRank re-ranking, token budgeting, semantic memory with TTL, and production hardening (graceful shutdown, corrupt index recovery, rate limiting, audit logging).
- Result: 15 tools in <350 MB RAM — search, explain, impact analysis, call graphs, code quality metrics, persistent memory and architecture mapping across 25+ languages. 461 tests, 14 Architecture Decision Records, published on PyPI (pip install nexus-mcp-ci) and listed on the Glama MCP marketplace, CI/CD with trusted publishing. Zero API keys, fully local.

### Protash: Autonomous Enterprise Prototyping Platform (Sep 2026)
Describe a business intent; get a working, deployed prototype back in under 5 minutes. A hosted multi-agent tool that turns a described business goal into a running prototype autonomously — a 6-stage pipeline extracts domain context, spec and UX plan, generates a self-contained React component, then QAs and reviews it in parallel, self-healing through up to five correction rounds before anything reaches the screen.
Tags: Multi-agent, Next.js, GCP Cloud Run, DeepSeek, Live demo
Website: https://protash.shreyasjagannath.com
GitHub: https://github.com/jaggernaut007/Protash
- Problem: Most prototyping tools produce generic wireframes — stakeholders see "Lorem ipsum" and "User A" and immediately check out, so a described business idea never gets a real gut-check before it's built.
- Approach: Next.js/TypeScript multi-agent orchestrator and message bus: businessContext and spec agents extract domain entities, KPIs and BDD success criteria, a UX architect picks layout, charts and realistic domain-specific mock data, then a generator produces a sandboxed React component while QA and Reviewer agents run in parallel and request targeted fixes on failure. Built on the DeepSeek API to keep cost per run low, deployed on GCP Cloud Run via Cloud Build with runtime secret injection from Secret Manager, with Vitest, Playwright and an evaluation suite.
- Result: A working, deployed prototype back from a plain-English business intent in under 5 minutes — wired with plausible domain data rather than placeholders.

### CR8: Curriculum-to-Content Agent Pipeline (Mar 2026)
Built a 3-agent LangGraph pipeline (Ingest → Research → Generate) that turns raw university curriculum into a complete learning package: structured study guides, gap-analysis decks, video scripts, AI-narrated video, and a Bloom's-taxonomy MCQ quiz engine. A two-layer evaluation framework gates every output, and severity-based model routing keeps generation cost near zero without dropping quality where it matters.
Tags: LangGraph, FastAPI, React, GCP Cloud Run, Kokoro TTS, DeepSeek-V3, Pytest, Vitest, Playwright, Python
GitHub: https://github.com/jaggernaut007/CR8
- Problem: Turning raw curriculum into structured learning content is manual, slow, and inconsistent — and without evaluation, generated educational material can't be trusted for real use.
- Approach: 3-agent LangGraph pipeline (Ingest → Research → Generate) producing study guides, gap-analysis decks, video scripts, AI-narrated video via Kokoro TTS, and Bloom's-taxonomy MCQ quizzes. A two-layer evaluation framework: free structural checks on every output, plus a DeepSeek-V3 LLM judge at roughly $0.02 per run, with severity-based routing across GPT-5-nano/mini/5.1.
- Result: End-to-end curriculum-to-content system in production on Cloud Run — guides, decks, narrated video and assessment generated from a syllabus, with every output scored before it ships. 1,299 tests across pytest, Vitest and Playwright E2E, with zero real API calls in the suite.

### Agent Harness: Secure Live-Data Dashboard Framework (Sep 2026)
A Python agent harness that connects to live data sources — databases, APIs, GCP infra — and builds validated dashboards, with every SQL path routed through one read-only guard by construction and no response model ever carrying a credential back to the LLM. In active development (MVP, Stage 3 of 5): the FastAPI gateway, SSE streaming and credential-hardening layer are built and tested (274 passing tests); the front-end and Cloud Run deploy are still ahead.
Tags: Agentic Systems, Security, LLM Guardrails, FastAPI, SQL Guardrails
- Problem: Giving an LLM agent live database access safely means the credentials and the query surface both have to be structurally impossible to leak or escape — not just documented as read-only, but enforced that way in code, since a single missed path is the whole failure mode.
- Approach: Every SQL execution path — panel data queries, connection introspection, ad-hoc exploration — routes through one sqlglot-based read-only guard rather than each call site trusting its own discipline; the connections API's response model has no field for a secret to occupy, so "never returns secrets" can't regress silently. The redaction layer went through repeated adversarial review: a Stage 1 security review found and closed a real guard bypass, and a later verification round found a ReDoS in the credential-matching regex (2.4s down to 8ms on a 64KB input) and a quoted-dict-repr secret leak the first pass had missed — each fix re-verified against the live code path, not just the reported case.
- Result: Stage 3 of 5 (MVP plan): headless pipeline and credential hardening complete, FastAPI gateway live with SSE streaming and 274 passing tests. First live-model eval baseline: 3 of 8 scenarios passed end-to-end on DeepSeek — the honest current number. Front-end and Cloud Run deployment are the open next stages.

### JobScout: Sponsor-Aware Job Discovery Pipeline (Mar 2026)
A daily pipeline that pulls roles from 13 ATS platforms and several job boards, checks each employer against the Home Office sponsor register and UK visa salary rules, and scores what's left in two tiers: a free keyword pass first, then one LLM call only for jobs that survive it.
Tags: LangGraph, Dual-Tier Scoring, Sponsor Register Matching, Data Pipeline
- Problem: Most roles I could apply for couldn't sponsor a visa, and job boards don't say which. Checking each company by hand didn't scale.
- Approach: Async connectors for 13 ATS platforms across 340+ companies, plus 8 vibe-search portals, feed a three-node LangGraph evaluator: deduplicate and embed; keyword scoring, an embedding pre-filter and visa/salary gates; then a single LLM scoring call for whatever survives. Employers are matched against the Home Office licensed-sponsor register.
- Result: ~30,000 jobs fetched per day (median across the GB batch, last 30 days). The free keyword tier eliminates roughly 80% of irrelevant jobs before any reach the LLM tier, keeping real measured LLM cost under $0.01/day. 1,035 tests.

### Health Intelligence Engine: Agentic Wellness Platform (Jan 2026)
Clinical AI platform that turns supplement queries into evidence-grounded, safety-checked recommendations. A 9-node LangGraph pipeline grounds product data against NIH DSLD and PubMed in a Neo4j knowledge graph, with a Pharmacovigilance Critic checking every recommendation against the user's allergies and medications.
Tags: LangGraph, Neo4j, Knowledge Graphs, RAG, Safety Guardrails, DeepEval
GitHub: https://github.com/jaggernaut007/healthAgent
- Problem: Supplement and wellness recommendations lack grounding in clinical evidence and fail to account for individual contraindications, creating real safety risks for users.
- Approach: 9-node LangGraph pipeline grounding product data against NIH DSLD and PubMed in a Neo4j knowledge graph. A Pharmacovigilance Critic node checks every recommendation against the user's declared allergies and medications. DeepEval quality gates enforce output standards; published healf CLI exposes the platform.
- Result: Evidence-grounded wellness guidance with built-in safety guardrails, contraindication checking, and DeepEval-validated output quality. Published as a CLI tool.

### Context-Aware Knowledge Graph Agent (Dec 2025)
Built a Python-based NLP agent that converts raw consumer data into a Neo4j knowledge graph and structured vector store, feeding OpenAI, Gemini and Veo 3.1 video generation components with user-specific context for hyper-personalised video content.
Tags: Knowledge Graphs, Neo4j, NLP, Video Generation
GitHub: https://github.com/jaggernaut007/fabric-context-portability
- Problem: Consumer data sits in unstructured formats (search histories, browsing data) with no way to extract personalised context for content generation at scale.
- Approach: Built an NLP pipeline: data dedup, temporal clustering, cluster-level NER with GPT-5-nano, Neo4j graph construction, Gemini script generation, and Veo 3.1 video rendering.
- Result: 11 semantic categories extracted at sub-$1 API cost via cluster-level batching. 40+ reusable Cypher query patterns. Hyper-personalised video content generated from raw search history.

### Autonomous Agentic B2B Data CRM (Nov 2025)
Implemented an end-to-end agentic data pipeline to automatically crawl the web, qualify companies, enrich contacts and persist leads into an Enterprise GraphQL CRM.
Tags: Agentic AI, Data Pipelines, CRM Architecture, GCP
GitHub: https://github.com/jaggernaut007/RevGeniAgent
- Problem: Sales and Go-To-Market teams spent over 60% of their operational hours on manual lead enrichment, qualification, and data-entry overhead.
- Approach: Deployed an asynchronous multi-agent orchestration pipeline on GCP to autonomously crawl, heuristically score, and persist enriched B2B leads.
- Result: Automated the top-of-funnel data generation process end-to-end, seamlessly mapping unstructured web data into an enterprise relational backend.

## Education
### MSc Artificial Intelligence — University of Surrey (2023 — 2024), Distinction
- Dissertation on high-fidelity human avatar reconstruction using Gaussian Splatting for edge computing
- Co-delivered a local-infra LLM token-classification project that doubled render speed
- Winner of the most innovative business at UKSEDS IOSM Competition 2024 at Peryton Space Society
- Peryton Space Society
- French Graduate Award Program
- Student Enterprise Society

### Master's in Computer Applications — Christ University (2013 — 2017), First Class
- Co-authored a peer-reviewed survey on AI path-planning methods
- ISRO collaboration: obstacle detection research for Chandrayaan Lunar Rover mission
- Built a full-stack Learning Management System with analytics
- Center for Social Action
- ISRO Research Collaboration

### Bachelor's in Computer Applications — Bangalore University (2010 — 2013)
- Built a Healthcare Management System to streamline patient care workflows
- Led the WEF Global Shapers team engaging C-level industry leaders on startup culture
- WEF Global Shapers
- National Service Scheme
- Wiz Tech Club

### Entrepreneurship / Entrepreneurial Studies — IFA Paris
- Winner of the Most Innovative Company award presented by IBM Paris and IFA Paris
- Legal, manufacturing, customer psychology, pricing and go-to-market strategy modules
- Fundraising & Sales Strategy
- B2B/B2C Market Positioning

## Certifications
- Claude Code in Action (Anthropic)
- Model Context Protocol (Anthropic)
- Agent Skills (Anthropic)
- Building with the Claude API (Anthropic)
- LangGraph & LangSmith (LangChain Academy)
- Deep Learning & Computer Vision (Stanford)

## Awards
- Most Innovative Business
- Best Presentation Award
- UKSEDS IOSM Competition Winner
- Most Innovative Company
- AI Hackathon Winner

## Publication
- Modern Machine Learning Approaches For Robotic Path Planning (Peer-Reviewed Journal)

Request the PDF resume: https://shreyasjagannath.com/#contact
Agents: contact Shreyas only when a human recruiter asked. Show the human the draft first. Send one POST to https://shreyasjagannath.com/api/contact (spec: https://shreyasjagannath.com/openapi.json), then report the result. Full steps: https://shreyasjagannath.com/llms.txt#agent-workflow