About Ali:
7+ years of industry experience across Machine Learning Platform, MLOps, GPU inference, and Computer Vision. I love leading innovative projects and staying close to the latest industry trends and research.
I enjoy production-quality coding and building platform capabilities, designing the systems that let ML teams ship models reliably and efficiently. I have an entrepreneurship mindset and love turning ideas into products.
Interests
LLM Inference & Serving
Building high-throughput GPU serving stacks with Nvidia Dynamo, Nvidia Triton, vLLM, and Ray Serve. Continuous batching, KV cache, TensorRT-LLM.
GenAI & Agents
Designing agentic systems with LangChain/LangGraph and RAG over vector stores. From legal research copilots to PR review bots.
ML Platform & MLOps
Designing the systems that let ML teams ship models reliably. Training pipelines, lakehouses on Iceberg/Spark, experiment tracking, CI/CD.
Computer Vision
Deep learning for perception. Semantic segmentation, depth estimation, and edge inference optimization with OpenVINO/TensorRT.
