Technical Lead - Compute Platform and Optimization

About the role

We are looking for an experienced software engineer to own performance and the compute platform that underpins our autonomous off-road driving stack. This role spans middleware performance, system-level tuning, and compute optimization.

Responsibilities

• 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

Requirements

• 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

Qualifications

• Experience with GPU programming and optimization (CUDA, TensorRT, model quantization/pruning, ahead-of-time compilation)
• Familiarity with ROS2 middleware, DDS implementations (CycloneDDS, FastDDS), or shared-memory transports (iceoryx)
• 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

Skills

• Experience with GPU programming and optimization (CUDA, TensorRT, model quantization/pruning, ahead-of-time compilation)
• Familiarity with ROS2 middleware, DDS implementations (CycloneDDS, FastDDS), or shared-memory transports (iceoryx)
• 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

Benefits

• Salary range: $200K to $260K annually
• Equity compensation
• Best-in-class healthcare, dental and vision plans
• Unlimited PTO
• 401k with company match
• Parental leave

Pay

$200K to $260K annually

Schedule

Full-time