Available for remote and hybrid opportunities

Tushar
Jadhav

AI/ML Engineer — Production Agentic AI

I build LangGraph multi-agent systems, hybrid RAG pipelines, and LLM-powered enterprise applications that actually work in production — not just in demos.

10K+
Queries / Day
<400ms
RAG Latency
92%
NER F1 Score
2.5+
Years Production AI
tushar@prod ~ agent-system

Production AI, not tutorial AI.

I'm an AI/ML Engineer at Vishleshan AI Solutions with 2.5+ years of production experience. I specialize in building systems that go beyond prototypes — handling real traffic, real edge cases, and real business constraints.

Currently pursuing M.Tech in AI & Data Science from IIT Patna alongside full-time work. My focus areas are LangGraph-based agentic systems, hybrid RAG architectures, and multilingual NLP for Indian enterprise use cases.

I've diagnosed silent LangChain batching bugs, fixed BM25 indexing on structured payloads, and dropped embedding latency from 15 seconds to 0.1 seconds by switching to local inference — the kind of problems that only appear when you build for production.

LangGraph FastAPI Qdrant pgvector Groq Gemini RAGAS Docker AWS ECS Celery
🧠

Agentic AI Systems

LangGraph Supervisor Agents orchestrating specialised subagents with stateful multi-step reasoning.

🔍

Production RAG

Hybrid retrieval with RRF reranking, RAGAS evaluation, and sub-400ms latency at enterprise scale.

🌐

Multilingual NLP

Hindi, Hinglish, and English pipelines for Indian enterprise use cases — search, translation, extraction.

🎓

M.Tech AI @ IIT Patna

Pursuing M.Tech in Artificial Intelligence & Data Science from IIT Patna (2026–2028).

Things I've shipped.

Production systems with real users, real traffic, real constraints.

ENTERPRISE PRODUCTION
Commercial Vehicle AI Search

Hybrid RAG pipeline for a major vehicle manufacturer. Dense semantic + BM25 sparse retrieval with RRF reranking. Multilingual Hindi/Hinglish/English support with intent classification and multi-turn conversation via Redis session history.

10K+ Queries/Day
<400ms Latency
Qdrant OpenAI FastAPI Redis AWS ECS BM25 + RRF
SAAS PRODUCT
Anuva.ai — Multilingual Translation SDK

JS embed SDK that translates any website in real-time using Sarvam AI. Single script tag injection — zero code changes on client side. Stale-while-revalidate Redis caching for near-zero perceived latency. Supports Hindi, Marathi, Tamil, and 10+ Indian languages.

JavaScript SDK React Component Sarvam AI Redis FastAPI AWS EC2 Cloudflare
ENTERPRISE NLP
BERT NER Pipeline — Document Intelligence

Production NER pipeline for identification document extraction at JSW GBS. 92% F1 score across 150+ fields processing 5,000+ documents per day. Projected to eliminate 11 FTEs annually through automated document understanding.

92% F1 Score
5K+ Docs/Day
11 FTEs Saved
Hugging Face BERT spaCy Doctr FastAPI OCR

The stack I work with daily.

🤖

Agentic & LLM

LangGraph LangChain CrewAI RAG Pipelines RAGAS Prompt Engineering Multi-Agent
🧪

LLM APIs

OpenAI Anthropic Claude Gemini Groq LLaMA Sarvam AI Hugging Face Ollama

Backend & APIs

Python FastAPI Celery Redis REST APIs WebSockets SQLAlchemy
🗄️

Vector & Databases

PostgreSQL pgvector HNSW + GIN Qdrant MongoDB ChromaDB Supabase
☁️

Cloud & DevOps

AWS ECS AWS ECR AWS S3 Docker GitHub Actions Vercel Railway
🎨

Frontend & Embed

Next.js React JavaScript JS SDK Clerk Auth Tailwind HTML/CSS

Where I've built.

Vishleshan AI Solutions
Jan 2026 – Present
AI/ML Engineer — Full-time · Andheri, Maharashtra
  • Built LangGraph Supervisor Agent orchestrating RAG Agent and Web Search Agent for dynamic multi-step query resolution in production.
  • Designed hybrid RAG pipeline with Qdrant (dense + BM25 sparse + RRF reranking) serving enterprise search at sub-400ms latency.
  • Delivered AI smart search + chatbot as a single JavaScript snippet — zero frontend code changes on client websites.
  • Built Anuva.ai — multilingual website translation SaaS with JS SDK, Redis caching, and Sarvam AI LLM backend.
  • Fine-tuned CLIP VLM by freezing encoder layers and training custom projection heads on domain-specific datasets.
JSW GBS Pvt. Ltd
Mar 2024 – Dec 2025
Automation & AI Developer · Navi Mumbai, Maharashtra
  • Built BERT NER pipeline — 92% F1 across 150+ fields, processing 5,000+ documents/day in production.
  • Developed IDP system using OVIS VLM + OCR + FastAPI — projected to eliminate 11 FTEs annually.
  • Delivered real-time email auto-response using LangChain Agentic AI + RAG + LLaMA on Groq.
  • Engineered resume parsing engine using spaCy, OCR, and regex for structured candidate profiling at scale.
Precihole Sports Pvt. Ltd
Jul 2023 – Oct 2023
Software Developer · Navi Mumbai, Maharashtra
  • Increased workflow efficiency by 20% via Python and JavaScript automation within ERPNext.
  • Designed Power BI dashboards using MySQL and REST APIs for real-time sales performance tracking.

Let's build something real.

Open to remote and hybrid AI Engineer roles. If you're building something ambitious with LangGraph, RAG, or agentic AI — let's talk.

tusharj071@gmail.com