Robotics Research Engineer: Production-Ready Perception & ML

xdof, Inc.; San Mateo, Northern (CA, KY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

XDOF, Inc. in California is seeking a Research Engineer to bridge research prototypes to production-grade code running reliably on embedded hardware.

You’ll move across perception, ML, and data infrastructure to ship real-time systems and optimize performance from CPU to GPU. Ideal candidates have strong C++ (modern standards), CUDA, Python for ML, and experience profiling, debugging, and containerizing workloads with Docker.

Qualifications

• 3+ years of industry software engineering with a focus on systems, performance, or production ML.
• Strong C++ proficiency (C++17/20) with memory management and performance-conscious coding patterns.
• CUDA programming experience: ability to write, profile, and debug GPU kernels.
• Proficiency with Python and familiarity with ML frameworks (PyTorch, TensorFlow) to read/modify research code.
• Comfort with Linux systems, including build systems, debugging tools, and containerization.

Responsibilities

• Making research prototype code production-grade for reliable execution on embedded hardware.
• Hardening a perception pipeline for real-time performance on embedded platforms.
• Profiling and optimizing performance across CPU, memory, and GPU levels.
• Writing and debugging CUDA kernels for acceleration of compute-heavy workloads.
• Integrating research outputs into production code with testing, error handling, and observability.
• Containerizing workloads (Docker) so they can be deployed by the infrastructure team.
• Collaborating with researchers to balance accuracy, latency, and resource usage.

Skills

C++ (modern)

CUDA

Python for ML

Linux systems

Performance profiling

TensorRT/ONNX

Tools

Docker

Nsight

CUDA profiling tools

Job description

XDOF, Inc. in California is seeking a Research Engineer to bridge research prototypes to production-grade code running reliably on embedded hardware.

You’ll move across perception, ML, and data infrastructure to ship real-time systems and optimize performance from CPU to GPU. Ideal candidates have strong C++ (modern standards), CUDA, Python for ML, and experience profiling, debugging, and containerizing workloads with Docker.