Infra and ML engineer. Spent the last few years doing Kubernetes, GPU inference, and LLM serving — mostly trying to make things run faster and cheaper.
Co-founded June Labs, built a voice AI stack that hit sub-400ms E2E latency. Before that, infra at DynamoAI and DevOps at Bizongo.
Currently working on June, an AI contract review tool for legal teams.
Stack: Python · Go · TypeScript · Kubernetes · vLLM · TensorRT-LLM



