Open to opportunities

Pranav Kudale

@pranavkudale

Message

I build production LLM backends, RAG systems, and MLOps pipelines.

India

Message

What I'm looking for

I'm targeting AI Engineer, LLM Engineer, Generative AI, Applied AI, and MLOps roles where I can build production LLM pipelines, RAG systems, reliable backend APIs, and observable ML workflows.

At NeuraMach.AI, I lead backend AI development for ScoreVedaa, shipping 40+ REST APIs for personalized CAT preparation, performance analytics, prediction, and subscription billing. I architected an 18-state LLM conversational flow and reduced inference costs by 63% through deterministic routing, validation, token caps, and cost guardrails.

I've also built production FastAPI systems for the Everlign Readiness Engine, cutting API latency by about 65% and adding PostgreSQL advisory locks and a configurable JSON rule engine for reliable, dynamic policy evaluation.

I build RAG and ML products end to end, including a research-paper recommendation engine using SPECTER2, FAISS, DeBERTa, and Groq, plus a CodeT5 vulnerability detector that achieved 76.53% F1.

Experience

Work history, roles, and key accomplishments

Current

Full Stack Engineering Intern

Current

NeuraMach.AI

Feb 2026 - Present (6 months)

Led backend AI development for core product features including goal setup, performance analytics, and subscription billing. Architected an 18-state LLM conversational flow, reduced inference costs by 63%, and shipped 40+ REST APIs with 250+ tests.