Agentic AI systems
built for measurable ROI.
I'm Shreyas Jagannath— I pair sharp problem diagnosis with production engineering to ship enterprise-grade AI that holds up in the real world: guardrailed, instrumented, and built to pass compliance in regulated environments.
Fast, without the fragility.
Rapid prototypes with guardrails, evaluations, and compliance built in from day one — not bolted on after.
Shreyas Jagannath
Senior AI Engineer · Forward Deployed / Applied AI · 8+ yrs · London, UK
Verified Impact
10x
Cost reduction via multi-agent token optimization
<350mb
RAM footprint bypassing PyTorch for optimized ONNX
Zero /s
Downtime during Monolithic-to-Microservices split
3x
Agent efficiency gain (60s → 20s) on core calibration feature
55%
Latency cut on a healthtech platform in critical-failure alpha
100%
AI crash failures eliminated; GDPR/AI Act compliance audit delivered
About
Production AI for environments where it has to work
From computer vision (2016) to enterprise AI consulting, full-stack systems, production LLMs, and now agentic AI — always with real users, measurable outcomes, and increasingly in regulated, safety-critical settings.
At Klyft, beyond building the core agentic workflows, I developed observability pipelines that surfaced an early signal: the generated plans were calibrated for high-performance users, while most of the actual user base were everyday consumers. Flagging this early helped the team adjust product direction before it became a retention problem. I enjoy this intersection of engineering and product thinking — using system behaviour and evaluation data to improve both architecture and outcomes.
Diagnose
Align stakeholders on success criteria, constraints, risks, and what “good” looks like.
Architect
Choose the right trade-offs: guardrails, evaluation strategy, data contracts, and system boundaries.
Ship
Deliver production systems with instrumentation, reliability hardening, and iteration cycles.
The frontier timeline
A wave-by-wave narrative of shipped systems
Started not as a software engineer but as a researcher solving a genuinely hard spatial perception problem for a space mission. Mono vision depth detection — making a rov…
Signal: Thinking about AI as a tool for solving hard real-world problems before most people were using the word 'AI' in their job titles. The origin of the computer vision seed.
Immediately after research, went hands-on with production software building a food delivery platform, order processing, and bulk automation with Java, Spring, MySQL. Not…
Signal: The full-stack foundation. Understanding systems end to end — databases, APIs, business logic, infrastructure. This is the layer beneath everything built later.
Delivering AI solutions across wildly different industries — automotive (TVS Motors), retail (Target), aerospace (Airbus), logistics (Volvo), fintech (Varthana), payments…
Signal: Learned how AI lands — or fails to land — in real enterprise contexts. The diagnostic instinct starts here: 'what problem are you actually trying to solve?' before proposing a solution.
Built a company merging AI/AR virtual try-on engines and an NLP-driven visual RAG search system. Embedded on the floor with retail clients, watched how their staff actual…
Signal: Leading people and building systems simultaneously. Translating a customer's floor-level problem into a technical architecture with real stakes.
Owned the full technical direction. Built a Designer AI Assistant using RAG over design documents, and a manufacturing lifecycle platform. Researched Gaussian Splatting a…
Signal: Technical roadmap ownership. Pragmatic trade-offs and shipping systems. Knowing when NOT to build is as valuable as knowing how to build.
Deployed multi-agent orchestration, LLM inferencing, memory systems, RAG pipelines, observability, MLOps, and CI/CD. Reduced token usage by 10x through prompt optimisatio…
Signal: Operating at the production edge of agentic AI. Applying the consulting diagnostic instinct to observability data to advise a go-to-market pivot.
Inherited a Flutter + GCP platform in critical-failure alpha. Built a guard-railing and validation layer across Vertex AI integrations, eliminated 100% of AI crash failur…
Signal: Breadth of production AI experience—greenfield build, iterative product development, and rescue engineering in regulated environments.
Shipped three live production systems in four months independently: an infrastructure tool solving the token cost of file browsing (Nexus-MCP), an end-to-end agentic appl…
Signal: When between roles, I ship. Three live production systems built independently in four months — proving continuous, hands-on building at the production edge of agentic AI.
Projects
Recent Work
Selected projects spanning agentic AI, knowledge graphs, developer tooling, and creative interfaces.
Nexus-MCP: Hybrid Code Intelligence Server
Designed and built a unified MCP server with 15 tools that reduces AI agent token usage by 70–90% through hybrid search (vector + BM25 + code graph), structural analysis and persistent memory — published on PyPI and listed on the Glama MCP marketplace, <350 MB RAM, 25+ languages, 461 tests, 14 ADRs.
Quality Gate CI: AI-Powered Compliance Pipeline
A fail-closed compliance CI pipeline prototyped end-to-end in under 5 hours for a pharma client. Claude Code Actions auto-generates Gherkin and pytest-bdd/Playwright tests from acceptance criteria and code diffs, enforcing a deploy gate that surfaces audit evidence directly on every PR before merge.
Health Intelligence Engine: Agentic Wellness Platform
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.
Deployments & Architecture
Production Systems Shipped
From rescuing failing healthcare systems to cutting token costs by 10x — solving hard problems at the architectural level.
Lead AI Engineer (Founding Team)
Lead Software Engineer (Pro Bono)
Lead AI Engineer (Founding Team)
Lead Software Engineer / CTO
Software Consultant
Full Stack Engineer (Founding Team)
AI Researcher Intern
Skills
Technical Expertise
Core competencies spanning AI research, software engineering, and cloud infrastructure.
Agentic AI & LLM Systems
AI / ML
Engineering
Cloud & Infrastructure
Reliability & Governance
Recognition
Awards, Certifications & Research
Most Innovative Business
Best Presentation Award
UKSEDS IOSM Competition Winner
Most Innovative Company
AI Hackathon Winner
Modern Machine Learning Approaches For Robotic Path Planning
Peer-Reviewed JournalEducation
Academic Background
MSc Artificial Intelligence
University of Surrey
2023 — 2024
- 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
Master's in Computer Applications
Christ University
2013 — 2017
- 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
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
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
Contact
Let's Connect
I'm currently open to new opportunities as a Senior AI Engineer, AI Platform Engineer, Lead Engineer (AI Products), or build-heavy Applied AI / Forward Deployed Engineer. Let's build something impactful.