Description
Solerity is hiring an ML Deployment Engineer to move video, image, speech, and text analytics models from research prototypes to production inference services in Kubernetes or similar environments. The role involves requirements gathering, Python-based CI/CD and packaging around NVIDIA Triton Inference Server, TensorRT execution providers, and Business Logic Scripting, pipeline tuning, testing, documentation, deployment best practices, and system-level problem resolution. The position requires a Top Secret clearance with Full Scope poly, a bachelor’s degree or equivalent experience, 14+ years of software engineering experience, strong Python and DevOps skills, containerization and Kubernetes experience, and production ML deployment experience. Benefits include medical, dental, and vision coverage, flexible onsite, hybrid, or remote work, retirement and life insurance, paid time off, tuition assistance, and other employee benefits.
