About this role
Member of Technical Staff - Inference Research at Modal. Location: New York City or San Francisco. Role: conducting research, training speculators, deploying models Requirements: Research-leaning or systems background in LLM inference; experience with kernels, quantization, schedulers, and autoscaling; record of shipping research/systems; able to take research bets end-to-end and work onsite in NYC or San Francisco. Category: Engineering Seniority: Senior Level Tools: Flash Attention 4, Python Commitment: Full Time Workplace: Onsite Languages: English