Software Engineer II, MLOps Framework

Responsibilities

• Architect and implement model conversion and compilation pipelines using ONNX, TensorRT, and torch.compile for deployment on edge devices such as NVIDIA Orin.
• Maintain and evolve the model release registry to ensure traceability and reproducibility across model versions and target platforms.
• Perform latency benchmarking and model quality parity evaluations against safety-critical performance requirements.
• Compare performance metrics across hardware platforms to validate latency and accuracy compliance before release.
• Collaborate with model development teams and stakeholders to translate findings into reliable, actionable outcomes.

Requirements

• Bachelor's degree in Computer Science, Electrical Engineering, Robotics, or a related field plus 4+ years of relevant experience, or a master's degree plus 2+ years of relevant experience.
• Extensive experience with model conversion and compilation pipelines using ONNX, TensorRT, and torch.compile.
• Experience performing latency benchmarking and model quality parity validation.
• Hands-on experience deploying and testing models on edge hardware such as NVIDIA Orin or similar embedded platforms.
• Experience maintaining a production model release registry.
• Ability to interpret performance metrics across hardware platforms against strict latency and accuracy requirements.
• Preferred experience with PTQ, QAT, mixed-precision inference, multi-target model releases, autonomous-driving perception algorithms, multi-modal sensor fusion, C++, and CUDA kernel development.

Benefits

• 100% employer-paid medical, dental, and vision premiums for full-time employees.
• 401(k) plan with a 6% employer match.
• Flexible schedule and generous paid vacation available immediately after the start date.
• AD&D and life insurance.
• Full-time role with bonus and stock-option components included in the compensation package.