Member of Technical Staff - Research, Inference

📋 Description

• Own end-to-end inference research bets across models
• Develop speculative decoding and disaggregated prefill/decode
• Work on quantization (FP8, INT4) and KV-cache management
• Optimize memory management and autoscaling for serverless traffic
• Collaborate with customers and Forward Deployed Engineers to deploy models

🎯 Requirements

• Research-leaning or systems background in LLM inference
• Fluency in the LLM serving stack from kernels to schedulers
• Track record shipping research or systems others build on
• Drive to take a research bet from idea to result
• Ability to work in-person in NYC or San Francisco

🎁 Benefits

• In-person collaboration in NYC or SF offices
• Work with cutting-edge AI infrastructure
• Collaborative, mission-driven team culture