2027 Internship Onboard Infrastructure Engineer, ML Inference

The role

You will integrate LLM and VLA models into a Rust middleware stack for autonomous heavy machinery. You will optimize model execution on edge compute and validate performance on heavy autonomous machinery at test sites.

What you will do

• Integrate open-source and proprietary LLM/VLA models into the onboard Rust middleware stack.
• Profile and optimize model execution using TensorRT, vLLM, ExecuTorch or custom edge inference runtimes.
• Streamline sensor tokenization to feed real-time streams to models.
• Identify and eliminate bottlenecks across memory bandwidth, compute, and IPC.
• Validate performance optimizations on heavy autonomous machinery at test sites.

Required qualifications

• Currently pursuing a BS, MS, or PhD in Computer Science, Electrical/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 modern systems concepts: multithreading, OS and GPU scheduling, memory management, asynchronous programming and IPC.

Nice to have

• Practical experience deploying neural networks on constrained hardware using TensorRT, ONNXRuntime or ExecuTorch.
• Experience with LLM/VLA optimization techniques such as KV-cache management, FP8/INT4 quantization, continuous batching or speculative decoding.
• Exposure to multi-modal/VLA models or robotics frameworks.

Before you apply

• Designed strictly for students (undergraduate or graduate).
• Opportunities for full-time conversion are highly limited.

About the company

Bedrock retrofits heavy equipment with autonomy to move AI onto real job sites. The team includes veterans from Waymo, Segment, and Uber Freight.