•Design, build, and implement scalable software solutions supporting deployment of machine learning workloads on hardware accelerators used in production environments.
•Develop internal platforms and automation tools using Python and JavaScript to improve developer
workflows, testing reliability, and deployment efficiency.
•Deploy and maintain services across cloud and containerized environments using Docker, Kubernetes, and
CI/CD pipelines, improving release stability and observability.
•Rapidly prototype new engineering approaches for model deployment and runtime optimization, enabling faster
experimentation and iteration for applied ML products.
•Collaborate with cross‑functional teams including infrastructure engineers, data scientists, and product
stakeholders to deliver monetizable platform capabilities.
•Lead the creation of automated testing frameworks and performance monitoring systems, increasing code
coverage and identifying regressions earlier in the development cycle.
