Member of Technical Staff, Inference

📋 Description

• Productionize model checkpoints end-to-end from research to production
• Build and optimize large-scale multi-GPU inference systems
• Design/implement diffusion-model serving infra for real-time workflows
• Add monitoring/observability for new releases: errors, throughput, GPU, latency
• Collaborate with research teams to collect data and support model development
• Explore/integrate GPU inference providers (Modal, E2E, Baseten)

🎯 Requirements

• 4+ years of ML model inference at scale in production
• Strong experience with PyTorch and multi-GPU inference for large models
• Kubernetes for ML workloads—deploying, scaling, debugging GPU-based services
• Comfortable working across multiple cloud providers and managing GPU driver compatibility
• Experience with monitoring/observability for ML systems (errors, throughput, GPU utilization)
• Self-starter who can work embedded with research teams and move fast

🎁 Benefits

• Salary range: $240,000-290,000 USD
• Remote-friendly, globally distributed team
• Opportunity to impact millions of users