Edge ML Ops Engineer: Model Conversion & Deployment

Torc Robotics, Inc.; Northern (KY); Hybrid; USD 139,000 - 167,000; Full time

Benefits offered by this job

Stock options

401K match

Paid medical/dental/vision

Job summary

Torc Robotics, Inc. is seeking a Software Engineer for the ML Ops Framework & Conversion team to own end-to-end model conversion, compilation, and release workflows for edge devices.

You’ll work with perception and safety teams to ensure models meet strict latency and accuracy requirements for autonomous trucking. You will drive pipelines using ONNX, TensorRT, and torch.compile, maintain a model release registry, and benchmark performance across platforms to ensure robust, safe deployments.

Qualifications

• Bachelor's degree in Computer Science, Electrical Engineering, Robotics, or related field plus 4+ years of experience; or Master's degree plus 2+ years.
• Extensive experience with model conversion and compilation pipelines (ONNX, TensorRT, torch.compile) and latency/quality parity validation.
• Hands‑on experience deploying and testing models on edge hardware (e.g., NVIDIA Orin or similar).
• Experience maintaining a model release registry in a production environment.
• Ability to compare performance metrics across hardware platforms to validate latency and accuracy requirements.

Responsibilities

• Architect and implement model conversion and compilation pipelines for edge deployment.
• Maintain and evolve the model release registry for traceability and reproducibility.
• Perform latency benchmarking and quality parity evaluations for safety-critical performance.
• Compare metrics across platforms to verify accuracy and latency before release.
• Collaborate with model development teams and stakeholders to translate findings into actionable outcomes.

Skills

Model deployment

Cross-team collaboration

Latency benchmarking

Data-driven decision making

Education

Bachelor's degree in CS/EE/Robotics or related

Master's degree (preferred)

Tools

ONNX

TensorRT

torch.compile

Job description

Torc Robotics, Inc. is seeking a Software Engineer for the ML Ops Framework & Conversion team to own end-to-end model conversion, compilation, and release workflows for edge devices.

You’ll work with perception and safety teams to ensure models meet strict latency and accuracy requirements for autonomous trucking. You will drive pipelines using ONNX, TensorRT, and torch.compile, maintain a model release registry, and benchmark performance across platforms to ensure robust, safe deployments.