p
parthkeskar

Parth Keskar

@parthkeskar

AIML Engineer, RAG, FastAPI And MLOps Specialist

India
English, Hindi, Marathi
About me
build production-grade AI systems, not just notebooks. I help businesses deploy custom RAG engines (LangChain, FAISS, ChromaDB) to eliminate AI hallucinations, and optimize ML inference using FastAPI (benchmarked at <8ms latency). I also engineer robust, headless data pipelines and track all experiments with MLflow for full reproducibility. Whether you need a broken pipeline fixed, a model deployed, or a custom AI agent built, I deliver clean, documented code that works. Let's talk.... Read more

Skills

p
parthkeskar
Parth Keskar
Offline • 
Average response time: 1 hour

See my services

AI Integrations
I will fix your broken python, langchain, or rag pipeline
From$90 / projectMore details

Work experience

Freelance

Independent AI/ML Engineer

Freelance • Self-employed

Feb 2026 - Present • 8 mos

Designed and deployed production-grade AI systems including: End-to-end MLOps churn prediction engine (79.7% accuracy, 7.4ms p95 inference latency via FastAPI) Automated market sentiment pipeline with headless async ingestion and FinBERT classification Enterprise RAG engine using LangChain, FAISS, and ChromaDB to eliminate LLM hallucinations All systems tracked with MLflow, version-controlled via Git, and deployed with monitoring dashboards