Senior Data, AI Systems & Full-Stack Engineer

Venu Madhav Sambarapu

Building production Python backends, cloud data warehouse & OLAP systems, Next.js full-stack data products, and stateful agentic AI.

Experienced in taking initiatives from technical architecture through to deployed, containerized solutions — spanning FastAPI & PostgreSQL/pgvector backends, multi-engine OLAP data warehouses (Snowflake, BigQuery, Redshift, ClickHouse, DuckDB), Next.js 16 & React 19 full-stack applications, LangGraph stateful multi-actor agents, and GCP serverless Cloud Run / Terraform infrastructure.

Roles:AI / GenAI EngineerPython Backend EngineerFull-Stack DeveloperSenior Data EngineerCloud / SRE Engineer

Explore Projects Ask AI Assistant View Resume 📄

GCP · AI · OLAP

4+ Yrs IT(+11 Acad.)

Senior Data, AI & Backend

6 OLAP Engines

Snowflake · BigQuery · DuckDB

Next.js 16

React 19 · FastAPI · pgvector

GCP & Agents

LangGraph · Vertex AI · Terraform

Engineering Specializations

Detailed Skill Matrix →

⚡

Backend, OLAP & Data

Python Backend & Data Warehousing

Asynchronous FastAPI services, multi-warehouse OLAP benchmarking & FinOps guardrails, production ETL/ELT pipelines, and PostgreSQL/pgvector semantic search.

PythonFastAPISnowflakeBigQueryClickHouseDuckDBPostgreSQL/pgvectorsqlglot

Explore Data & OLAP →

🧠

Stateful Agents & RAG

Generative & Agentic AI

Dynamic tool calling, cyclic agent workflows with LangGraph checkpoints (MemorySaver), in-memory BM25 retrieval, and prompt injection safety guards.

LangGraphVertex AILangChainIn-Memory RAGGuardrails

View Agent Systems →

☁️

Full-Stack & Cloud SRE

Full-Stack Web & Cloud Infrastructure

End-to-end Next.js 16 & React 19 products, containerized GCP Cloud Run microservices, Pub/Sub streaming, Terraform IaC, and autonomous SRE incident response.

Next.js 16React 19TypeScriptGCP Cloud RunTerraformDocker

View Full-Stack & Cloud →

Featured Flagship Projects

All Projects →

Flagship AI & Vector Product

HireCraft — Closed-Loop Technical Job Discovery & AI Resume Crafter

Production-grade platform integrating direct career API ingestion (Greenhouse, Lever, Ashby), 768-dimensional dense vector matching in PostgreSQL (pgvector, <18ms), truth-preserving Google XYZ metric generation, and sub-second ATS-compliant PDF generation with verified 96.4% parse rate.

Architecture →Skills & Tech Stack →

Cloud Data Warehouses & FinOps

Cloud Data Warehouse & OLAP Benchmarking Suite

Comparative evaluation framework and Python benchmarking harness across Snowflake, BigQuery, Redshift Serverless, Databricks SQL, ClickHouse, and DuckDB (2M NYC Taxi rows, Q1–Q5) with sqlglot AST validation and FinOps spend guardrails.

GitHub Repo ↗Architecture →

Full-Stack Data Product

DatasetRadar — Dataset Intelligence Platform

End-to-end system monitoring news & journal sites to automatically detect cited public datasets via self-hosted LLMs, vector deduplication (pgvector), and a confidence-gated human review queue.

Demo Slides →Architecture →

GCP & Multi-Agent SRE

Autonomous Cloud SRE Copilot on GCP

Production-grade SRE copilot using Vertex AI Gemini multi-turn tool calling, Pub/Sub log event streaming, and 1-click chaos simulation with zero-downtime automated rollback.

GitHub Repo ↗Architecture →

Stateful AI Agents

LangGraph Playground Monorepo

Modular Python monorepo for engineering and deploying stateful, multi-actor agent workflows: dynamic tool-calling, conversational session checkpointers (MemorySaver), and self-healing SQL guardrails.

GitHub Repo ↗Patterns →

In-Memory RAG & Safety

Portfolio AI Assistant & In-Memory RAG

Hardened conversational assistant featuring zero-database in-memory BM25 retrieval (< 0.1ms latency), deterministic prompt injection defense guardrails, and dual-provider auto-failover.

Chat Assistant →Architecture →

Interactive AI Portfolio Assistant

Trained on my project specs, cloud data warehouse benchmarks, ETL architectures, and agent implementations. Ask anything or click a sample question:

Launch Assistant ✦

✦ What change can you bring to our company?✦ Cloud Data Warehouse OLAP Benchmarks ✦ Tell me about GCP SRE Copilot ✦ How does DatasetRadar detect datasets?✦ Explain LangGraph agent architecture ✦ Summarize background & skills

Experience & Education

Senior Data Engineer

4+ Years IT Experience

Factly Media and Research · Dec '21 – Present · Hyderabad, IN

Architecting full-stack data products, applied AI/LLM engineering (LangChain, LangGraph, RAG, pgvector), automated ETL pipelines, and internal validation suites powering the Dataful public datasets platform.

Prior Academic ExperienceAssistant Professor · Various Engineering Institutions · Aug '10 – Nov '21 (11+ Years) — Undergraduate engineering pedagogy in digital electronics, communication systems, and data analytics; NAAC accreditation analytics and Python workshops.

Education & Certifications

Post Graduate Certification in Data Science

IIIT Bangalore & upGrad · Aug '20 – Mar '21 · Secured 90%

M.Tech, Digital Electronics & Communication Systems

Mahaveer Institute of Science and Technology · Jan '12 – Jan '15

End-to-End Data Product Delivery

I take a project from a written spec and architecture doc all the way through to a fully working system with a real API, database, and frontend — not just prototypes. HireCraft and DatasetRadar are my proof: on HireCraft, I architected a production-grade, closed-loop technical job discovery and AI resume tailoring platform (Next.js 16, React 19, FastAPI, PostgreSQL pgvector 768d semantic matching, truth-preserving Google XYZ metrics, and sub-second ATS PDF generation); on DatasetRadar, I built a complete data-intelligence platform with semantic search, a self-hosted LLM detection pipeline, a confidence-gated human review UI, and Docker deployments — not partial builds, shipped products.

Applied AI/LLM Engineering

I build dense 768d semantic search, truth-preserving metric generation (Google XYZ framework), retrieval-augmented Q&A, embedding-based deduplication, Vertex AI agentic tool calling, and stateful multi-actor agent workflows using LangChain, LangGraph, and Google Cloud Vertex AI — I layer AI onto real systems and structured monorepos rather than bolt it on as a standalone demo.

Agent/Skill Engineering

I design reusable, composable AI skills and stateful graph architectures (such as my LangGraph Playground Monorepo and GCP SRE Copilot) that encode an entire team’s conventions — directory structure, coding standards, validation rules, cyclic tool-calling loops, and checkpoint-backed persistent memory — into self-correcting workflows, complete with safety scaffolding like branch checks, query guardrails, and step-by-step rollback. This is a distinct capability from writing pipelines by hand: I build the tooling that lets a team, or an agent, reliably reproduce my standards without me in the room.

Production Automation & Agentic Ops

I build systems that run unattended on a schedule, touch real infrastructure — cloud telemetry, chat, git, version control — and get hardened over multiple iterations based on real failures. From my Autonomous Cloud SRE Copilot on GCP that triages live Pub/Sub incident streams to scheduled failure resolvers opening pull requests, I design safeguards, like branch checks, human-in-the-loop approvals, and reply-detection fallbacks, so an autonomous process doesn’t do the wrong thing, and knows when to stop and ask for help.

Cloud Data Warehousing, OLAP Benchmarking & Core Data Engineering

Beyond ETL scraping, schema validation, and catching subtle pipeline bugs, I architect and benchmark analytical data warehouse layers across Snowflake, Google BigQuery, AWS Redshift Serverless, Databricks SQL (Photon), ClickHouse, and DuckDB. My Cloud Data Warehouse Comparison & Benchmarking Suite runs standardized 2M-row OLAP workloads (Q1–Q5), validates multi-dialect SQL ASTs in CI via sqlglot, and enforces FinOps spend guardrails (AUTO_SUSPEND, byte-scan caps, RPU limits) alongside ACID, Time Travel, and open table format (Apache Iceberg / Delta Lake) governance.