ML Deployment Engineer

ML Deployment Engineer moves video, image, speech, and text analytics (VISTA) models from research prototype to production inference services. Collaborate cross-functionally with researchers and end users. Build CI/CD and packaging around Python on NVIDIA Triton Inference Server with TensorRT. Tune pipelines for throughput. Create user documentation and deployment best practices. Resolve system problem reports.

TS/SCI clearance with polygraph. Bachelor's degree in Computer Science or related discipline (or 4 additional years experience). 14+ years software engineering experience. Strong Python, DevOps, CI/CD, Docker, Kubernetes. Experience taking projects from prototype to production. Software development in C++, Java, GoLang, CUDA. Production ML systems support. Familiarity with NLP, Computer Vision, ASR, Video Processing. ONNX, TensorRT knowledge.