Software Engineer 2 (Hybrid)
Core
Deploy video, image, speech, and text analytics (VISTA) models from research prototypes to production inference services for federal government customers.
Role type
Senior ML Deployment Engineer
Builds
Production inference services running on Kubernetes or similar environments
Domain
Federal government / Machine Learning Operations
Deliverable
production ML models
Required skills
Python, DevOps, CI/CD, Docker, Kubernetes, Model deployment, System design, Requirements analysis
Preferred skills
C++, Java, GoLang, CUDA, NLP, Computer Vision, ASR, Video Processing, ONNX, TensorRT
Technologies
Python, NVIDIA Triton Inference Server, TensorRT, Docker, Kubernetes, ONNX
Responsibilities
Collaborate with end users and researchers to understand requirements and align development; Build CI/CD and packaging around Python on NVIDIA Triton Inference Server; Tune pipelines for throughput and support customer transition; Review and test software components against design requirements; Create comprehensive user documentation and establish deployment best practices; Resolve system problem reports and contribute to system design including hardware/software trade-offs.
Seniority
Senior, hands-on IC
