Onboard ML Inference Engineer for Heavy Machinery

Bedrock Robotics Inc; San Francisco (CA); On-site; USD 52,000 - 60,000; Part time

Job summary

Bedrock Robotics Inc. seeks an Onboard Infrastructure Intern to bridge frontier AI and real-time execution on autonomous heavy machinery. You will integrate LLMs and VLA models into Bedrock's core stack, ensuring multi-billion parameter models run within strict edge compute budgets.

You will work with Rust or C++, optimize model execution, and validate performance on real autonomous equipment at Bedrock test sites. This internship offers hands-on experience in AI at the edge.

Qualifications

• Pursuing BS/MS/PhD in CS, ECE, Robotics or related field.
• Proficiency in Rust or C++, with PyTorch or JAX experience.
• Solid foundation in GPU architectures, CUDA, or parallel computing.
• Understanding of modern systems concepts: multithreading, OS and GPU scheduling, memory management, IPC.

Responsibilities

• Integrate open-source and proprietary LLM/VLA models into our onboard Rust middleware stack alongside existing perception, planning and control pipelines.
• Profile and optimize model execution using TensorRT, vLLM, ExecuTorch or custom edge inference runtimes tailored for NVIDIA Jetson Thor.
• Streamline sensor tokenization (cameras, LiDAR) to feed real-time streams directly to models without latency spikes in vehicle control loops.
• Identify and eliminate bottlenecks across memory bandwidth, compute, and IPC using tools like Nsight Systems, Nsight Compute and eBPF.
• Validate your performance optimizations directly on heavy autonomous machinery at our test sites.

Skills

Rust

C++

Pytorch

JAX

CUDA

Multithreading

Education

BS/MS/PhD in CS/Engineering/Robotics

Tools

TensorRT

ONNXRuntime

ExecuTorch

NVIDIA Jetson

vLLM

Job description

Bedrock Robotics Inc. seeks an Onboard Infrastructure Intern to bridge frontier AI and real-time execution on autonomous heavy machinery. You will integrate LLMs and VLA models into Bedrock's core stack, ensuring multi-billion parameter models run within strict edge compute budgets.

You will work with Rust or C++, optimize model execution, and validate performance on real autonomous equipment at Bedrock test sites. This internship offers hands-on experience in AI at the edge.