Summary
Rahul Katre is a software engineer with 8 years of experience focused on accelerating LLM inference and production ML tooling, currently working on the Neuron SDK at Annapurna Labs/AWS. He has practical experience shipping inference and observability products at AWS (Amazon Managed Grafana) and contributed to ML and systems research while earning an MS in Computer Science from Georgia Tech. Rahul has hands-on experience across internships and research roles—building ads systems at Niantic, automated volatility trading tooling at GTS, and drone LTE systems for warehouse applications—demonstrating a blend of cloud, systems, and embedded networking expertise. He also taught graduate NLP at Georgia Tech, signaling strong communication skills and domain depth in language models. Colleagues describe him as an engineer who moves ideas from research to production, with a particular knack for optimizing inference stacks and developer-facing SDKs. Though early in a focused ML infra career, Rahul’s cross-domain background suggests an ability to navigate both low-level system constraints and high-level ML deployment challenges.
8 years of coding experience
3 years of employment as a software developer
MS Computer Science, MS Computer Science at Georgia Institute of Technology
English, Konkani