Internship 2027 Onboard Infrastructure Engineer, ML Inference
Bedrock Robotics Inc18 hours ago
Responsibilities
- Integrate open-source and proprietary LLM and VLA models into the onboard Rust middleware stack alongside perception, planning, and control pipelines.
- Profile and optimize model execution using TensorRT, vLLM, ExecuTorch, and custom edge inference runtimes for NVIDIA Jetson Thor.
- Streamline camera and LiDAR sensor tokenization for real-time model input without latency spikes in vehicle control loops.
- Identify and eliminate memory bandwidth, compute, and IPC bottlenecks using Nsight Systems, Nsight Compute, and eBPF.
- Validate performance optimizations directly on autonomous heavy machinery at test sites.
Requirements
- Currently pursuing a BS, MS, or PhD in Computer Science, Electrical or Computer Engineering, Robotics, or a related field.
- Proficiency in Rust or C++, with supporting experience in PyTorch or JAX.
- Solid foundation in GPU architectures, CUDA, or parallel computing.
- Understanding of multithreading, operating-system and GPU scheduling, memory management, asynchronous programming, and IPC.
- Practical experience with TensorRT, ONNX Runtime, or ExecuTorch on constrained hardware is a bonus.
- Experience with LLM/VLA optimization techniques such as KV-cache management, FP8/INT4 quantization, continuous batching, or speculative decoding is a bonus.
- Exposure to multimodal/VLA models or robotics frameworks is a bonus.
Categories
About Bedrock Robotics Inc
Bedrock Robotics builds autonomous control systems that retrofit heavy construction equipment, enabling driverless operation on large infrastructure and industrial projects. The San Francisco–based, privately held company, founded in 2024, deploys its technology with contractors and project owners to speed schedules and improve job-site safety. Its business centers on upgrading existing fleets and operating them in the field, with software, sensors, and integration services tailored to construction workflows.