Shreyas Jagannath
Building production AI systems that deliver measurable business value — from agentic platforms to computer vision engines.
About
Turning Ambiguous Goals into Production AI
I'm a Senior AI Engineer with over nine years of experience building and delivering production AI systems in startup and consulting environments. I specialise in translating ambiguous product goals into reliable, measurable AI solutions that meet roadmap commitments without compromising maintainability or performance.
In a recent role, I led the development of an agentic AI system where cost, latency, and user engagement were critical constraints. By redesigning agent orchestration, tightening prompt and context strategies, and introducing targeted evaluation and caching mechanisms, I achieved a 3× efficiency improvement. In parallel, I designed and shipped a new core feature that became the application’s most-used capability — both delivered within the planned roadmap.
My background spans agentic AI, NLP, computer vision, and cloud-native infrastructure. I've consistently taken AI features from concept to deployment — balancing tight timelines, infrastructure limitations, and evolving requirements. As a former CTO and multiple-time founding team member, I bring both technical depth and a product-aware perspective to every system I build.
I'm driven by building systems that are observable, scalable, and resilient in production — not just impressive in demos.
1class ShreyasJagannath:2 expertise = [3 "Agentic AI",4 "NLP",5 "Computer Vision",6 "RAG",7 ]8 experience = "9+ years"9 focus = "Production AI"10 location = "London, UK"Experience
Where I've Built
From founding teams to CTO roles — delivering production AI across industries.
Lead AI Engineer (Founding Team)
Klyft Technologies
- Delivered a multi-agent AI coaching platform for fitness, nutrition and behavioural change using Python, Google ADK, OpenAI and Gemini APIs on Vertex AI
- Engineered scalable GCP infrastructure achieving low-latency responses, 100% pilot uptime and a 10x reduction in serving costs
Lead AI Engineer (Founding Team)
Scan and Sew Inc.
- Implemented a generative AI assistant platform for 3D product designers using OpenAI LLM/VLM APIs and RAG
- Led research on Gaussian Splatting and PyTorch3D for spatially aware CAD 2D–3D workflows
- Built a real-time product manufacturing lifecycle tracking platform with ReactJS, AWS Lambda, GraphQL and DynamoDB
Chief Technology Officer
AIMAGE Technologies
- Designed an AI/AR virtual try-on engine using SLAM and 3D geometry with OpenCV, PyTorch3D, Mediapipe and Unity3D
- Developed an NLP-driven search and recommendation platform combining TensorFlow/PyTorch with a vector-database-backed visual RAG knowledge graph
Software Consultant
Mage Ventures
- Implemented a secure cross-platform payment gateway for Walmart-owned PhonePe across multiple client apps
- Built an AI-powered automated grocery checkout engine using computer vision and TensorFlow
Projects
Recent Work
Selected AI projects demonstrating expertise in agentic systems, knowledge graphs, and multi-agent orchestration.
Context-Aware Knowledge Graph Agent
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.
Multi-Agent NL-to-Code Orchestration
Prototyped a collaborative multi-agent AI system using Vercel AI, Next.js, OpenAI and Zod that translates natural-language feature requests into executable coding-pipeline architectures, reducing development time for new features.
Agentic Sales CRM
Implemented an end-to-end agentic Sales CRM with CrewAI to crawl the web, qualify companies, enrich contacts and persist leads into a Next.js/Prisma/GraphQL CRM backed by FastAPI on GCP Cloud Run.
Skills
Technical Expertise
Core competencies spanning AI research, software engineering, and cloud infrastructure.
AI & Machine Learning
Engineering
Cloud & MLOps
Recognition
Awards, Certifications & Research
Modern Machine Learning Approaches For Robotic Path Planning
Peer-Reviewed JournalEducation
Academic Background
MSc Artificial Intelligence
University of Surrey
2023 — 2024
- Researched Gaussian Splatting for neural human reconstruction
- Co-delivered a local-infra LLM token-classification project that doubled render speed
Master's in Computer Applications
Christ University
2013 — 2016
- Co-authored a peer-reviewed survey on AI path-planning methods
Entrepreneurship / Entrepreneurial Studies
IFA Paris
Bachelor's in Computer Applications
CMR University
2010 — 2013
- Built a Healthcare Management System to streamline patient care workflows
- Coordinated a local WEF Global Shapers team to engage industry leaders on startup culture
Contact
Let's Connect
Interested in discussing AI, exploring collaborations, or building something together? I'd love to hear from you.