Internship – Onboard Infrastructure Engineer, ML Inference

Bedrock Robotics

Onboard Infrastructure Engineering Intern integrating and optimizing LLM/VLA inference for Bedrock’s autonomous construction equipment. Building real-time Rust systems for safe, responsive heavy machinery.

Posted 9/10/2026internshipSan Francisco • California • 🇺🇸 United StatesEntry LevelWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in integrating LLM/VLA models into Rust middleware for autonomous systems, with a strong foundation in GPU architectures and performance optimization techniques. Proficient in deploying neural networks on constrained hardware and optimizing model execution for real-time applications.

Highest-signal resume keywords

Rust ProgrammingC++ ProgrammingTensorRT OptimizationGPU Architecture KnowledgeNeural Network Deployment

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

LLM/VLA IntegrationParallel ComputingMemory ManagementAsynchronous ProgrammingMultithreadingModel Optimization TechniquesKV-Cache ManagementFP8/INT4 QuantizationContinuous BatchingSpeculative Decoding

Tools & Technologies

NVIDIA Jetson ThorNsight SystemsNsight ComputeEBPFONNX RuntimeExecuTorchPyTorchJAX

Industry Keywords

Autonomous SystemsHeavy Construction EquipmentRoboticsReal-Time ProcessingJob-Site Safety

Tech Stack

Tools & technologies

C++PyTorchRust

About the role

Key responsibilities & impact

Integrate open-source and proprietary LLM/VLA models into Bedrock’s onboard Rust middleware stack alongside perception, planning, and control pipelines
Profile and optimize model execution using TensorRT, vLLM, ExecuTorch, or custom edge inference runtimes for NVIDIA Jetson Thor
Streamline camera and LiDAR sensor tokenization 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 Nsight Systems, Nsight Compute, and eBPF
Validate performance optimizations directly on heavy autonomous machinery at Bedrock test sites
Work on autonomous systems for heavy construction equipment, improving job-site safety and accelerating critical infrastructure schedules

Requirements

What you’ll need

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 multithreading, OS and GPU scheduling, memory management, asynchronous programming, and IPC
Practical experience deploying neural networks on constrained hardware using TensorRT, ONNX Runtime, or ExecuTorch 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 multi-modal/VLA models or robotics frameworks is a bonus
Legally authorized to work in the United States
Must be able to commute to the San Francisco location 3–4 days per week

Benefits

Comp & perks

Equal Opportunity Employer commitment
Reasonable accommodations during the hiring process
Opportunity to work on meaningful autonomous systems deployed in the real world
Opportunity to work alongside construction veterans and world-class engineers
Hands-on testing on heavy autonomous machinery at company test sites