Freelance AI Engineer · Full-stack · Jaipur, India

You bring the idea.
I build it and ship it to production.

I'm a freelance AI engineer, and you work with me directly - no agency layer, no account manager, no handoff to a junior. Enterprise RAG is my flagship. Below is the actual pipeline I build: scroll through it and you'll know exactly what you are paying for.

Freelance - you work with me directlyAvailable worldwide & remoteTaking new work
6+Years building
4Products launched
20+AI systems shipped
5+Enterprise clients

Services

AI agent, automation and RAG development services

Eight ways in, and one of them is the flagship. Every engagement is scoped and quoted before any build starts.

The flagship, stage by stage

How I actually build enterprise RAG

This is the pipeline behind every retrieval system I ship. Scroll it once and you will be able to tell whether anyone else's proposal is production-grade or a demo.

Your documentsSharePoint · Drive · S3Structure-awarechunkingEmbeddings+ metadata indexHybrid retrievalBM25 + vectorsReranking+ permissionsCited answeror "I don’t know"
Stage 01 of 06Ingestion
Stage 01 · Ingestion

Your documents, wherever they already live

Nothing gets migrated. Standard connectors read SharePoint, Confluence, Google Drive, Notion, S3 and most SQL or NoSQL databases in place, and anything unusual gets its own connector.

  • One source for a pilot, three to five for a full platform build
  • Permissions read at ingest, not bolted on afterwards
Stage 02 · Chunking

Chunking that respects how the document was written

Most failing RAG systems fail here. Splitting on character count shreds tables, headings and clause numbering, and no amount of prompt tuning recovers meaning that was destroyed on the way in.

  • Structure-aware splitting, chosen per document type
  • Headings, tables and lists survive the trip
Stage 03 · Indexing

Embeddings, plus the metadata you will actually filter on

Vectors alone cannot answer "the 2024 policy for the EU entity". Metadata is extracted and indexed alongside the embedding, so retrieval can filter before it ranks.

  • Embedding pipeline tuned to your corpus, not a default
  • Metadata filtering and multi-index search across business units
Stage 04 · Retrieval

Hybrid retrieval, never pure vector

BM25 + dense vectors + reranking, tuned to your corpus. Pure vector search ships demo-grade answers, not production ones.

  • BM25 catches exact terms, part numbers and clause IDs
  • Dense vectors catch the meaning that keywords miss
Stage 05 · Reranking

Reranking, with permissions applied before anything is shown

A reranker reorders candidates against the real question, and role-based access control drops anything the person asking is not cleared to see. This is where good retrieval becomes production retrieval.

  • Role-based access control and audit logs
  • Dynamic, permission-aware retrieval
Stage 06 · Answer

Citations on every answer - and "I don’t know" is a valid one

Every response links back to the exact document and section. "I don’t know" is a valid answer. Hallucinations are a bug, not a quirk.

  • Every response links to the exact document and section
  • An evaluation harness, so your team scores accuracy over time
  • Monitoring, logging, alerting and runbooks your on-call can operate

My own products

Built, launched, and running

Four products I designed and built myself. Every one is live - open them and see.

AI Learning Assistant · 2026

NirixAI

An AI learning assistant that turns YouTube videos, documents, and study materials into instant summaries, quizzes, and clear cited answers - so students master content without rewatching lectures or rereading pages. Built as a production RAG system on Pinecone with hybrid search, multi-LLM routing, and real-time streaming.

Serves streaming answers from a 20K+ content corpus with sub-2-second first-token latency.

LangGraph RAGHybrid SearchPineconeSSE Streaming
Natural-Language Database Agent · 2026

PiperQL

An open-source AI tool that lets anyone query a database in plain English instead of SQL - ops, finance, and HR teams ask a question and get the data plus the right chart, no analyst needed. Built as a LangGraph + OpenAI agent that turns natural language into SQL and holds conversation context.

Open-sourced under AGPL v3. Architecture scales to enterprise-grade query workloads.

LangGraph + OpenAINatural Language to SQLOpen Source
Trading Platform · 2025

Tim Edge

A trading platform for testing strategies and fixing bad habits: backtest on four years of broker-exact data, auto-journal every trade with its emotional context, and execute one-click through your own broker. Built full-stack with MetaAPI + Fyers integration, WebSocket streaming, Celery workers, and AWS.

Live execution through cTrader, IC Markets and Fyers on a 3-worker Celery architecture.

MetaAPIWebSocketCelery WorkersAWS
Trading Education Platform · 2025

Tim Academy

A trading-education program teaching rule-based ("mechanical") systems through self-paced courses, live monthly execution labs, and a performance-based certification. Built full-stack with live streaming, auth, and payments on Firebase.

Six proprietary systems delivered with 100ms live streaming and a certification track.

FirebaseLive StreamingPaymentsAuth

Client work

Systems I built for other people

Delivered for client teams and running in production. Brands stay unnamed; the architecture does not.

Enterprise RAG pipeline architecture

Retrieval Augmented Generation pipelines with hybrid search, optimised embedding pipelines, context-aware retrieval, and metadata-driven search, built for international brand workloads.

Hybrid SearchEmbedding OptimisationMetadata Filtering

Multi-index vector search system

An AI agent that searches several Pinecone indexes at once, with a universal metadata parser that normalises product fields across diverse catalogs - the pattern you need when retrieval has to span business units with different schemas.

Multi-Index PineconeUniversal Metadata Parser

AI assistant platform

Production AI assistants for several international brands - product recommendations, multilingual support, appointment booking, complaint handling, and FAQ automation, using fine-tuned models with ReAct reasoning chains.

Fine-Tuned ModelsMultilingualReAct Reasoning

Tech stack

What I build with

Stack-agnostic by principle - I pick tools to fit your problem, not a fixed toolkit. This is what I reach for most, and what the products above are actually running on.

AI engineering

LangGraphLangChainRAG systemsAgentic workflowsVector searchPinecone

Models

OpenAIClaudeMulti-LLM routingFine-tuningGenerative AI

Backend

PythonFastAPIFlaskDjangoMicroservicesHigh-concurrency APIs

Data

PostgreSQLMySQLMongoDBVector databasesPandasData pipelines

Infrastructure

AWSGoogle CloudDockerNginxLinuxCelery

Frontend

ReactNext.jsAngularJavaScript

How I work

Six standards I hold every build to

Whether it is a two-week audit or a four-month platform build, these do not move.

01

Architecture-first over prompt hacking

Every engagement starts with a retrieval architecture, not a prompt. Prompts are the last mile, not the first one.

02

Hybrid retrieval, never pure vector

BM25 + dense vectors + reranking, tuned to your corpus. Pure vector search ships demo-grade answers, not production ones.

03

Citations on every answer

Every response links back to the exact document and section. "I don’t know" is a valid answer. Hallucinations are a bug, not a quirk.

04

Production infrastructure, not notebooks

Monitoring, logging, alerting, auto-scaling, audit trails, and runbooks. Every deliverable is something your on-call can operate.

05

Your data stays in your cloud

Self-hosted, enterprise-API with zero data retention, or hybrid - chosen during the audit based on your compliance posture.

06

Handover, not dependency

Every engagement ends with your team able to operate and extend the system without me. No seat-licensing, no vendor lock.

Next step

Ready to build what you have in mind?

Bring your idea or a stuck project. We'll scope the architecture, map the build, and set a concrete plan. No sales pitch - just honest, actionable direction, straight from the person who would build it.