Software Engineer - Model Performance Systems

Highlights

• Define the roadmap for next-gen AI infrastructure diagnostics and benchmarking.
• Build tools to find the Pareto frontier of latency vs. cost vs. quality.
• Your tools will gatekeep what defines good performance for customers.

What they offer

• Meaningful equity (U.S. only)
• 100% coverage of medical, dental, and vision for employee and dependents
• Flexible PTO including company-wide Winter Break
• Paid parental leave
• Fertility and family-building stipend through Carrot (U.S. only)
• Company-facilitated 401(k)
• Exposure to ML startups for learning and networking

Ideal candidate

Systems-curious engineer who loves hardware, automation and understanding how LLMs really run. You thrive on vague problems, high ownership, and driving cross-team technical decisions.

Requirements

• Technical depth with strong communication skills to drive cross-team efforts
• Ability to navigate vague requirements and mentor other engineers
• Love for systems and hardware including GPU memory subsystems, InfiniBand and cluster data movement
• Automation mindset with passion for stress-testing and fuzz testing to find breaking points
• Mathematical curiosity about Transformers, FLOPs and memory requirements
• Familiarity with Python and eagerness to master NVIDIA software stack, C++ a plus