ML Engineering Lead | High-Performance Systems

As the Lead of the AI/ML Engineering Chapter at Glintt Global, I direct a team of 9 engineers building production-grade solutions. My expertise lies in bridging the gap between state-of-the-art R&D and mission-critical infrastructure, specializing in high-performance inference optimization using NVIDIA Triton and TensorRT.

I have a proven track record of deploying models at scale, including a CV/NLP system processing 15M+ monthly transactions while improving extraction accuracy from 76.9% to 98.7%. Whether pioneering Edge AI for industrial X-ray systems or architecting multi-agent RAG systems, my focus is always on low-latency, high-availability intelligence.