Inference Engineer

📋 Description

• Design and build low-latency, scalable inference stack for foundation models.
• Work with research and product engineers to ship fast, cost-effective products.
• Design and build robust inference infrastructure and monitoring.
• Have significant autonomy to shape products and AI across devices.
• Support real-time multimodal intelligence in production.
• Improve performance, reliability, and observability.

🎯 Requirements

• Strong engineering skills, navigate complex codebases with maintainable code.
• Experience building large-scale distributed systems with high performance.
• Technical leadership to execute zero-to-one results amid ambiguity.
• Background in inference pipelines with ML and generative models.
• Experience implementing state-of-the-art ML models to applied problems.
• Preferable: CUDA or Triton experience.

🎁 Benefits

• Compensation: Competitive base salary with equity
• Health Insurance: Fully covered medical, dental, vision
• Parental Leave: 9 weeks paternity, 12 weeks maternity
• 401(k) plan
• Commuter Allowance
• Flexible PTO