Headline

AI/ML Engineer | Low-Latency, High-Concurrency Systems | RAG, LLMs, FastAPI | IEEE | Production Systems

About

An AI/ML Engineer focused on building production-grade, low-latency ML systems with strong emphasis on scalability, reliability, and real-world impact. I design and deploy high-concurrency ML APIs (FastAPI) handling 160+ RPS, optimize inference pipelines, and build end-to-end systems combining predictive models with LLM-based reasoning (RAG). My work includes clinical AI systems (AUC ~0.98) and transaction risk scoring engines, with focus on explainability (SHAP), human-in-the-loop (HITL) decision systems, and robust evaluation. Interested in solving problems at the intersection of ML systems, GenAI, and production infrastructure. Currently exploring system design for ML at scale, observability, and fault-tolerant AI systems.

Location

Bengaluru

Work experience

AI/ML Intern at International Institute of Medical Science and Technology Council, Jan 2026 - Present · 5 mos, Bengaluru, Karnataka, India

Education

Bachelor of Engineering, Computer Science(Data Science), KNS Institute Of Technology

PUC, Science, SJRC Arts, Science and Commerce College, Race Course Rd, Bangalore-09

Public links

github: https://github.com/Nithin00614