About the Role
As an ML Systems Engineer on the Physical AI team, you will design and build platforms for scalable, reliable, and efficient serving of foundation models specifically tailored for physical agents. Our platform powers cutting-edge research and production systems, supporting both internal research discovery and external customer use cases for autonomous vehicles and robotics. The ideal candidate combines strong ML fundamentals with deep expertise in backend system design. You’ll work in a highly collaborative environment, bridging the gap between Physical AI research and production engineering to accelerate innovation across the company.
Responsibilities
- Build & Scale: Maintain fault-tolerant, high-performance systems for serving robotics-related models and foundation models at scale, ensuring low latency for real-time applications.
- Platform Development: Build an internal platform to empower model capability discovery, enabling faster iteration cycles for research teams working on robotics.
- Collaborate: Work closely with Robotics researchers and Computer Vision engineers to integrate and optimize models for production and research environments.
- Design Excellence: Conduct architecture and design reviews to uphold best practices in system scalability, reliability, and security.
- Observability: Develop monitoring and observability solutions to ensure system health and real-time performance tracking of model inference.
- Lead: Own projects end-to-end, from requirements gathering to implementation, in a fast-paced, cross-functional environment.
Requirements
- Experience: 4+ years of experience building large-scale, high-performance backend systems, with deep experience in machine learning infrastructure.
- Algorithm Optimization: Deep experience optimizing computer vision and other machine learning algorithms for cloud environments, including GPU-level algorithm optimizations (e.g., CUDA, kernel tuning).
- Programming: Strong skills in one or more systems-level languages (e.g., Python, Go, Rust, C++).
- Systems Fundamentals: Deep understanding of serving and routing fundamentals (e.g., rate limiting, load balancing, compute budgets, concurrency) for data-intensive applications.
- Infrastructure: Experience with containers (Docker), orchestration (Kubernetes), and cloud providers (AWS/GCP).
- IaC: Familiarity with infrastructure as code (e.g., Terraform).
- Mindset: Proven ability to solve complex problems and work independently in fast-moving environments.
Nice to Haves
- Exposure to Vision-Language-Action (VLA) models.
- Knowledge of high-performance video processing (e.g., FFmpeg, NVDEC/NVENC) or 3D data handling (point clouds).
- Familiarity with robotics middleware (e.g., ROS/ROS2) or AV data formats.