Get in touch

Open to new opportunities

AI Engineer — Portfolio 2026

UtkarshSingh

I'm an AI engineer with 11 years building production systems in financial services — now designing GenAI and agentic systems end to end, from RAG and eval harnesses to the CI that ships them.

Open to new opportunities
01 / About

Eleven years of backend. Now building agents.

I'm an AI engineer with 11 years building production backend systems in financial services — trading, money movement, and securities management — including four years embedded at Fidelity Investments as an EY consultant, delivering event-driven microservices and high-traffic investment platforms.

Now I design and ship GenAI and agentic systems end to end: tool-calling agents, multi-step orchestration, and RAG with hybrid retrieval across dense, BM25, and graph signals. I build the evaluation harness that gates promotion — golden datasets, versioned baselines, regression gates — so every retrieval and model change is measured before it ships. I also lead AI enablement for 200+ engineers across the institutional vertical.

/ Toolkit

Languages
Python, TypeScript, Go, Java, SQL
GenAI & Agents
RAG, Hybrid retrieval, LangGraph, CrewAI, MCP, LiteLLM, OpenAI SDK
Evaluation
Golden datasets, Regression gates, Guardrails, PII-aware handling
Backend
FastAPI, asyncio, Kafka, SSE streaming, Microservices
Infra & Data
AWS, Kubernetes, Terraform, PostgreSQL, Qdrant, Neo4j, OpenSearch
02 / Selected Work

Recent work in AI and systems.

02RAG Platform

Code Analyzer

2025

A code-intelligence platform that ingests and queries large multi-repository codebases — 600+ repos at its first engagement — to power software-engineering audits. A tri-store backbone pairs Qdrant for dense semantic search, Neo4j for call graphs and symbol references, and OpenSearch for BM25 exact-match on the rare identifier tokens embeddings handle worst, fused with Reciprocal Rank Fusion and cross-encoder reranking.

PythonQdrantNeo4jOpenSearchLiteLLM
03AI System

Resume Screener

2025

An AI resume-evaluation system on FastAPI that flags exact duplicates, near-duplicates, and semantic plagiarism through a multi-signal pipeline of hashing, lexical overlap, and embeddings — with PII-aware ingestion and human-reviewable evidence reports.

FastAPIEmbeddingsMinHash / LSH
07AI Platform

Meeting AI

2024

A meeting-intelligence platform that transcribes audio and generates structured minutes, summaries, and conversational Q&A using RAG over timestamped transcript segments, backed by PostgreSQL-native vector search. Inference sits behind a model-agnostic layer spanning OpenAI, Claude, Gemini, DeepSeek, Hugging Face, and Ollama, so quality can be benchmarked against cost and latency on noisy long-form audio.

PythonRAGpgvectorMulti-LLM
03 / Experience

Where I've spent my time.

Building the retrieval platform behind engineering audits, and the agents that automate enterprise onboarding.

  • Built Code-Analyzer, a code-intelligence platform that makes large commercial financial-services codebases auditable on a consulting timeline, treating retrieval over code as a problem distinct from retrieval over prose.
  • Built the evaluation harness that gates promotion — 30 hand-curated Q&A pairs across 15 indexed repositories, scored on keyword recall, file-pattern hit rate, cross-module recall, and citation rate against a versioned baseline. Hybrid retrieval holds 73% keyword recall at 520 ms, with 100% of answers citing sources.
  • Designed the TerraCore Onboarding Agent — an agentic system driving Terraform, Jenkins, and account-servicing APIs as LLM tools, cutting application onboarding from weeks to hours with resumable, auditable workflow state.
  • Shipped the agent as an async FastAPI service with SSE progress streaming, and made destructive infrastructure operations safe to automate through input validation, allow-listed actions, dry-run modes, and human-in-the-loop approval gates.
  • Leads AI enablement for 200+ engineers across the institutional vertical, covering agentic frameworks and org-scale GitHub Copilot adoption.

/ Education

2019 — 2020
M.S., Computer ScienceUniversity of Texas at San Antonio
2009 — 2013
B.E., Computer Science and EngineeringVisvesvaraya Technological University

/ Certifications

  • Databricks Accredited Generative AI Fundamentals
  • Developing Serverless Solutions on AWS
04 / Writing

Notes from building things.

05 / Contact

Let's build something good.

Have a project, a role, or an idea worth chasing? My inbox is open — I read everything and reply to most.