Senior Forward Deployed Engineer I (AI Inference)

📋 Description

• Embed with AI startups to deploy high-throughput LLM serving
• Own end-to-end design of multi-tenant AI inference systems
• Profile bottlenecks and optimize TTFT/TPOT in GPU clusters
• Collaborate with customers and internal AI infrastructure teams
• Architect distributed inference with Kubernetes-native tools
• Deliver production-grade, low-latency serving solutions

🎯 Requirements

• 6+ years in AI/ML systems or forward deployed engineering
• Hands-on with vLLM, llm-d, SGLang, TensorRT-LLM
• Proficient in Python or GoLang; know gRPC; Kubernetes
• Experience with distributed inference, caching, and batching
• Strong customer-facing communication and ownership
• Willing to travel up to 30%

🎁 Benefits

• Competitive compensation and equity
• Career development resources and external training
• Global benefits and flexible time off
• Equal opportunity employer commitment