A Sai Bharathai-backendRésumé ↗

A Sai Bharath

AI Backend Engineer

LLM Systems · RAG Pipelines · Agentic Workflows

Available for roles · Hyderabad, IN

I build production LLM systems — retrieval that stays fast and cheap when it can, and goes agentic only when a question genuinely needs it.

Query Routerready
Fast PathDataFusion
Agent LoopLangGraph
Latency1.42s
LLM Calls0
Tool Calls0/ 14

Submit a query — the gate takes the cheap deterministic path when it can, and spends on the agent loop only when a question needs it.

56
Users
95%
Accuracy
13
Stages
≤14
Tool Calls
Summary01 / 05

AI Backend Engineer specializing in production LLM systems — RAG pipelines, hybrid retrieval, and agentic orchestration.

About 17 months building and shipping AI systems: an enterprise AI analytics platform (async ingestion, hybrid retrieval, an agentic query engine) and a live ML product with 56 real users on the Chrome Web Store. Strong in Python, FastAPI, LangGraph, Azure OpenAI, and vector/graph retrieval — and opinionated about doing the expensive thinking at ingestion so queries stay fast.

role
AI Backend Engineer
focus
LLM · RAG · agents
shipping
~17 mo, production
based
Hyderabad, IN
status
open to roles
Experience02 / 05

NCR Atleos Associate Software Engineer

  • Building internal AI/automation tooling on production LLM and retrieval services.

NCR Atleos Software Developer Intern

  • Built a Graph RAG pipeline (LangChain + Neo4j) for internal developer tooling — context-aware Q&A over company knowledge bases via multi-step reasoning.
  • Engineered LLM services on Azure OpenAI with prompt pipelines, retrieval validation, and failure-handling for internal Q&A workflows.
  • Set up GitHub Actions CI/CD that removed manual deployment steps and kept dev and staging consistent across the team.
Selected Work03 / 05

Enterprise AI Analytics Platform

Freelance · private

FastAPI · LangGraph · OpenSearch · Azure OpenAI · Celery/Redis · PostgreSQL · DataFusion · Docker

A 13-stage async ingestion pipeline (Celery + Redis) that turns messy ERP/CSV into hybrid OpenSearch indexes (BM25 + HNSW) — intelligence computed at ingestion, never at query time. The query engine reranks with RRF and gates on a deterministic planner: high-confidence queries take a fast DataFusion path (~1–2s, zero LLM calls); multi-hop queries fall back to a LangGraph agent loop bounded to ≤14 tool calls. Value-validated joins via GIN-indexed array overlap, multi-tenant isolation at every layer.

TODO: replace with corrected freelance copy

Dockwave

Live

Next.js · FastAPI · LangChain · Neo4j · PostgreSQL · Azure OpenAI · AWS S3

Agentic document intelligence. Extracts entities into a Neo4j knowledge graph for context-aware Q&A across a whole workspace — catching cross-document connections plain vector search misses. A retrieval-grading loop runs 3–4 queries per question over 6–7 iterations, scoring by confidence to auto-select the best answer.

PhisX

56 users · Chrome Web Store

Python · Flask · React · AWS EC2 · Docker

Real-time phishing detection. An ML model at 95%+ accuracy served behind a live REST API (EC2 + Docker), shipped as a Chrome extension that flags phishing while you browse — 56 real users on the Chrome Web Store.

Personal Investor

In development

Next.js · Python · LangChain · Gmail API · Vercel

An AI-first personal finance tool. Reads credit-card data from Gmail and uses an LLM tool-selection engine that autonomously picks the right financial tool per query — no fixed query structure. Roadmap: real-time stock analysis and AI-generated portfolio insights.

Stack04 / 05
Techniques
RAG · hybrid retrieval (BM25 + HNSW) · RRF reranking · semantic routing · Graph RAG · agentic workflows · tool-calling · evaluation & guardrails · prompt engineering
Frameworks & Libraries
LangGraph · LangChain · FastAPI (async) · Celery + Redis · Pydantic · SQLAlchemy 2.0 (async) · asyncpg · PyArrow · React · Next.js
Datastores
PostgreSQL (incl. pgvector) · OpenSearch · Neo4j · MongoDB · DuckDB · Parquet · DataFusion
Languages & Infra
Python · TypeScript · Node.js · Azure OpenAI · Azure Blob · AWS (EC2 / S3) · Docker · GitHub Actions · CI/CD · Vercel
Contact05 / 05

Open to roles and interesting problems in AI backend and LLM systems. Fastest way to reach me: