Projects
Selected Projects
Work I'm proud of — product thinking, engineering, and things you can try live.
I'm Varun Mathur, an AI/ML Computational Science Senior Analyst at Accenture. I design and ship LLM-powered platforms, retrieval-augmented systems, and semantic search at enterprise scale — the kind of work that turns a proof of concept into something 19 engineers rely on.
Over the past three years at Accenture, I've moved from analyst to senior analyst while owning AI systems end to end — architecture, implementation, and production reliability. My work sits at the intersection of LLMs, retrieval systems, and distributed backend engineering.
Recent highlights: cutting response latency by 40% and production defects by 57% on an enterprise AI platform, pushing semantic search precision from 30% to 87% across 167K+ documents, and reducing hallucinated responses by 78% through systematic evaluation and prompt engineering.
Before Accenture, I trained GANs at Samsung R&D to improve computer vision robustness under real-world glare conditions. I hold a B.Tech in Electronics & Communications Engineering from VIT with a 9.03 CGPA, and I'm always glad to talk about what I'm building next.
A track record of taking generative AI from proof of concept to production, at enterprise scale.
The languages, frameworks, and infrastructure I use to take AI systems from idea to production.
Work I'm proud of — product thinking, engineering, and things you can try live.
Bachelor of Technology in Electronics & Communications Engineering
Jul 2019 — Jul 2023
I'm actively exploring new opportunities in AI/ML engineering. If you're hiring, or just want to talk shop about RAG systems and production LLM architecture, my inbox is open.
