Senior Software Engineer, Profiling Services

About the role

We are looking for a Senior Software Engineer to design and deliver an always‑on, low‑overhead GPU profiling service that operates in production at scale. The service will provide actionable performance insights for machine‑learning workloads across large clusters.

Key responsibilities

• Develop high‑reliability, low‑overhead implementations in C/C++ while respecting strict CPU and memory budgets.
• Lead end‑to‑end feature delivery across user‑mode components, driver/platform layers, and performance‑counter/trace providers.
• Define and integrate profiling models with existing ML/AI frameworks such as PyTorch and XLA to translate low‑level signals into actionable insights.

Required profile

• Bachelor’s or Master’s degree in Computer Engineering, Computer Science or related field, or equivalent experience.
• 5+ years of system‑level C/C++ development, including concurrency, memory management and performance engineering.
• Strong understanding of operating‑system fundamentals, computer architecture and performance analysis.
• Excellent communication skills and ability to influence cross‑functional teams.

Required skills

• C and C++ programming.
• CUDA programming and deep knowledge of GPU architecture.
• Experience with profiling and tracing stacks (CUPTI, Nsight, performance counters, event correlation).
• User‑mode driver development and integration with platform security models.
• Familiarity with ML ecosystems such as PyTorch and JAX.