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 · 9+ 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
0 → 1
Rapid zero-to-one prototyping to shipped feature within weeks
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.
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.
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 rigorous ops optim…
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 platform in critical-failure alpha. Diagnosed Vertex AI integrations, eliminated 100% of AI crash failures, cut latency by 55%, and conducted a GDPR/AI Act co…
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.
Multi-Agent Job Qualification Engine
An orchestrated multi-agent discovery pipeline that evaluates and scores open roles against a candidate's profile, deploying specialized AI experts across three distinct domains to surface highly qualified job matches.
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, <350 MB RAM, 25+ languages, 461 tests, 14 ADRs.
Career Intelligence Platform
Full-stack career analytics platform with a React frontend and FastAPI backend that uses Neo4j knowledge graphs, OpenAI and HuggingFace to analyse resumes, match jobs and deliver personalised career recommendations.
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)
Acting CTO (Pro Bono)
Chief AI Officer (Founding Team)
Chief Technology Officer
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
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 — 2016
- 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 Solution Architect, or Forward-Deployed Engineer. Let's build something impactful.