Bedrock Robotics
2027 Internship Onboard Infrastructure Engineer, ML Inference
San Francisco, CA · On-site · Internship · Posted Sep 10, 2026
- Education
- Currently pursuing a BS, MS, or PhD in a relevant field.
About the job
Integrate and optimize LLM and VLA inference on edge hardware for autonomous heavy machinery, meeting strict real-time execution deadlines.
What you'll do
- Integrate LLM/VLA models into the onboard Rust middleware and autonomy pipelines.
- Profile and optimize edge inference and sensor data processing for NVIDIA Jetson Thor.
- Diagnose performance bottlenecks and validate optimizations on autonomous machinery at test sites.
What they ask for
- Currently pursuing a BS, MS, or PhD in Computer Science, Electrical/Computer Engineering, Robotics, or a related field.
- Proficiency in Rust or C++, with experience in PyTorch or JAX.
- Solid foundation in GPU architectures, CUDA, or parallel computing.
- Understanding of multithreading, OS/GPU scheduling, memory management, asynchronous programming, and IPC.
Nice to have
- Experience deploying neural networks on constrained hardware using TensorRT, ONNXRuntime, or ExecuTorch.
- Experience optimizing LLM/VLA models or exposure to multimodal/VLA models or robotics frameworks.
Tools
Rust, C++, PyTorch, JAX, TensorRT, vLLM, ExecuTorch, NVIDIA Jetson Thor
AI focus
Integrate and optimize LLM/VLA models for real-time onboard inference, including sensor tokenization and model execution on edge compute.
Model-written summary · the original posting is authoritative