Autonomy Engineer - Deep Learning Model Acceleration
Core
Building and scaling infrastructure for high-performance deep learning inference and MLOps to support autonomous flight systems on edge devices.
Role type
Senior IC deep learning model acceleration engineer
Builds
High-throughput, low-latency inference solutions for Computer Vision and Vision Language Models on embedded hardware
Domain
Robotics / Computer Vision / Edge AI
Deliverable
production ML models
Required skills
MLOps, ML inference acceleration, edge deployment, Computer Vision fundamentals, GPU kernel development, ML framework expertise, model profiling, SDK development
Preferred skills
Vision Language Model (VLM) optimization, custom architecture implementation, training efficiency improvement
Technologies
CUDA, TensorRT, ONNX, PyTorch, TensorFlow, Docker, Kubernetes, CI/CD pipelines
Responsibilities
Develop high-performance inference solutions for CV workloads, profile models to identify bottlenecks, design end-to-end MLOps workflows, implement GPU kernels for custom architectures, create SDKs for external developers
Seniority
Senior, hands-on IC
