2 months ago
San Mateo, CA, USAMid Level
H1B sponsor
Responsibilities
- Productionize research prototypes for reliable, real-time execution on embedded platforms.
- Profile and optimize CPU, memory, and GPU performance using tools such as perf, NSight, and custom microbenchmarks.
- Write, profile, and debug CUDA kernels for compute-heavy workloads.
- Integrate research outputs into production code with testing, error handling, and observability.
- Containerize and package workloads with Docker for scaling and deployment by the infrastructure team.
- Collaborate with researchers to balance accuracy, latency, and resource usage.
- Hand off production-ready workloads to orchestration and compute infrastructure.
Requirements
- 3+ years of industry software engineering experience focused on systems, performance, or production ML.
- Strong C++ proficiency, including modern C++, memory management, and performance-conscious coding.
- Experience writing, profiling, and debugging CUDA GPU kernels.
- Experience with CPU performance optimization, cache behavior, SIMD, and latency reduction.
- Proficiency with Python and familiarity with PyTorch or TensorFlow sufficient to read and modify research code.
- Comfort with Linux systems, build systems, debugging tools, and containerization.
- Preferred experience shipping research or prototype code, working with real-time or embedded systems, and building perception, computer vision, or robotics systems.
- Preferred experience optimizing model inference with TensorRT, ONNX Runtime, or similar tools.
- Understanding of the lifecycle from research notebook to containerized, monitored production service.
About XDOF
XDOF builds data, software, and operational infrastructure for robotics companies and research labs developing general‑purpose robots and physical AI. It provides scalable data collection, tooling, hardware integration, and services that help teams train, deploy, and manage autonomy systems. The company is privately held and positions itself as an infrastructure partner to frontier labs and robotics builders, with a team drawing experience from Tesla, Google, Applied Intuition, BAIR, Covariant, and Gatik.