Machine Learning Infrastructure | Inference | Distributed SystemsCurrently working on - Quantization, speculative decoding, KV cache outing, and prefill-decode disaggregation.As a senior backend engineer with 5+ years of experience in machine learning systems, full-stack development, system design, and architecture for distributed cloud applications. I have worked across large scale distributed systems spanning from startups to large enterprises. Some of the tools that I am proficient in - Languages and frameworks - Python, Java, Go, Django, RailsDatabases - PostgreSQL, MongoDB, MySQL, Oracle, Redis, Memcached