The opportunity
Nuro leverages many different bench-top systems to evaluate and regression test different aspects of the software and hardware integration layer.
What you'll do
How will my new ML model affect contention on the GPU?
How does a new data format impact onboard logging rate or network contention: as more data might be flowing from through the system?
How much memory should be allocated for this new module, and how does it fit into the overall system budget?
Benchmarking Infrastructure: Develop and maintain the job orchestration layer that schedules, executes, and validates autonomy performance benchmarks across a fleet of physical bench-top systems — integrated into CI/CD pipelines as merge-blocking and release-blocking quality gates.
Platform Reliability & Observability: Build monitoring, alerting, and self-healing automation for the bench fleet. Proactively identify systemic risks — capacity bottlenecks, hardware degradation patterns, infrastructure single points of failure — before they become outages. Track utilization, failure rates, and capacity trends to ensure the platform scales ahead of organizational demand.
Performance Data Pipelines: Design and build end-to-end data pipelines that capture fine-grained performance metrics (CPU/GPU utilization, memory bandwidth, E2E latency, scheduling jitter) from bench-top runs, process them at scale, and surface actionable insights through dashboards and automated regression detection.
What they're looking for
- Statistical Analysis & Experimentation: Work with Data Science to develop: rigorous experimentation methodology for performance results from non-deterministic autonomy workloads — including variance analysis, significance testing, and regression detection. Bare-Metal & OS Platform: Guide the SRE team through the OS and system-level configuration of bench hardware — including Linux kernel tuning, boot infrastructure, networking, and hardware bring-up — ensuring the platform faithfully reproduces production robot compute behavior.
- Drive Platform & Allocation Strategy: Own the planning lifecycle for the benchmarking fleet across hardware generations. Partner with engineering and program leadership to negotiate hardware allocation, model utilization scenarios under real-world constraints, and present data-backed trade-off recommendations — balancing testing coverage, user throughput, cost, and SLA commitments against finite physical resources.
- Cross-Functional Collaboration: Partner with Hardware Engineering, NPI (New Product Introduction), SRE (Site Reliability Engineering), Perception, Behavior, and Data Science teams to translate their performance analysis needs into robust, self-service infrastructure.
- Experience: 3+ years of industry software engineering experience.
