Member of Technical Staff - Research, Inference
Modal · New York City, United States; San Francisco, United States · Full-time
Team: Engineering Department
Posted: 2026-07-05
Pay: USD 150000 – USD 350000 per year
The Member of Technical Staff for Research, Inference will lead end-to-end research initiatives to optimize LLM serving performance, specifically focusing on reducing cost per token and tail latency. The role involves developing and deploying advanced inference techniques such as speculative decoding, quantization, and memory management while collaborating with engineering teams to integrate these solutions into the platform.
Skills & tags: llm inference, speculative decoding, quantization, kv-cache management, distributed systems, gpu infrastructure, autoscaling, kernel optimization, machine learning engineering, serverless computing
View and apply at the original posting
Postings belong to their employers; this page links to the source.