Technical Lead - Compute Platform and Optimization
$200,000–$260,000 year
On-siteSeattle, Washington, United States
Job Summary
Profile and optimize middleware and inter-process communication (ROS2, DDS, shared-memory transports) to minimize latency and maximize throughput across the autonomy stack. Identify and resolve system-level performance bottlenecks across CPU, GPU, memory, and I/O. Work directly with algorithm developers to profile their code, identify optimization opportunities, and co-design implementations that meet real-time budgets. Build automated performance regression testing into CI so degradations are caught before merge. Write high-performance clean C++ code and promote good coding practices throughout the software organization. Think holistically about the system: understand how changes in one area affect the whole, contribute improvements beyond your core domain, and help raise the bar for the entire engineering organization.
Required Qualifications
- BS in computer science, electrical engineering, or a related field with 7+ years of relevant experience, or MS/PhD with 5+ years
- Strong background in systems engineering, performance optimization, or compute platform development
- Strong C++ and Python development skills
- Familiarity with Linux systems programming, including profiling tools (perf, nsight, vtune), kernel tuning, and resource management
Desired Qualifications
- Experience with GPU programming and optimization (CUDA, TensorRT, model quantization/pruning, ahead-of-time compilation)
- Experience with ROS2 middleware, DDS implementations (CycloneDDS, FastDDS), or shared-memory transports (iceoryx)
- Familiarity with high performance GPU compute platforms for robotics and AI applications
- Experience optimizing real-time systems with hard latency constraints
- Experience with large-scale build systems and CI/CD infrastructure
- Contributions to open-source middleware or performance tooling
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.