Senior DL Software Engineer, Model Optimization and Edge Deployment - Autonomous Vehicles

What you'll do

• Develop state-of-the-art model optimization techniques for real-time robotic execution.
• Implement advanced compression methods like quantization and pruning to reduce model size without sacrificing accuracy.
• Design high-performance inference strategies including automated sharding and efficient attention kernels.
• Conduct detailed layer-by-layer profiling to identify and resolve compute and memory bottlenecks.
• Automate deployment pipelines using PyTorch ecosystem tools for TensorRT conversion.

What we're looking for

• Expert-level proficiency in PyTorch or similar ML frameworks.
• Proven experience training, deploying, and optimizing large-scale DL models.
• Deep familiarity with NVIDIA’s TensorRT and CUDA SDKs.
• Experience implementing low-bit inference techniques for efficiency.
• Strong background in GPU architecture and high-performance kernel development.
• Active contributions to open-source libraries like vLLM and TensorRT-LLM.
• Understanding of real-time robotics constraints, including safety-critical determinism.