Performance Engineer, Inference Systems

📋 Description

• Run cross-layer perf investigations across throughput and latency to find root causes.
• Own and improve the correctness evaluation pipeline across hardware; lead regression investigations.
• Build observability and modeling tools for throughput, latency, reliability, and correctness.
• Partner with kernel, serving, routing, autoscaling, and capacity teams to land key optimizations.
• Rank opportunities by impact and effort; decline low-value items.

🎯 Requirements

• Hands-on perf engineering: profiling, roofline analysis, latency/throughput optimization, and root-cause investigation.
• Proficiency in Python; read, instrument, and contribute to large production codebases you didn’t write.
• Solid data analysis skills (e.g., SQL, pandas) to turn telemetry into clear findings.
• Ability to communicate quantitative results clearly in writing to influence priorities on teams you don’t manage.
• Genuine interest in correctness as an engineering discipline: numerics, evaluation design, regression detection.
• Experience with ML systems, especially training or inference infrastructure or large-scale inference.

🎁 Benefits

• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space