We're seeking a Software Engineer to bridge the critical gap between cutting-edge ML research and production-ready solutions. You'll transform research prototypes into robust, deployable systems that end users can confidently put into production. This role uniquely combines software engineering, DevOps practices, and ML solution delivery. Productionize ML Research: Transform research code and prototypes from our ML team into reliable, scalable solutions ready for end-user deployment Build Diverse Solutions: Develop applications and services in C++, Java, or Python; create gRPC-based containerized solutions with clients in Java, Python, or GoLang Own the Delivery Pipeline: Design and maintain CI/CD pipelines, ensuring smooth deployment from development to production Deploy ML Infrastructure: Configure and optimize containers using NVIDIA Triton Inference Server for high-performance inference Performance Engineering: Profile, tune, and optimize solutions for production workloads Documentation & Best Practices: Create comprehensive user documentation and establish deployment best practices Collaborate Cross-Functionally: Work directly with end users to understand requirements and with researchers to align development with real-world needs This job also offers telework once the candidate is familiar with the environment
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Mid Level