Tech Lead Manager (ML Systems)

TL;DR

Tech Lead Manager (ML Systems): Building and optimizing an internal distributed framework for LLM training and evaluation with an accent on system performance and scalable infrastructure. Focus on optimizing training and inference frameworks, integrating SOTA technologies, and implementing post-training methods like RLHF and GRPO.

Location: Must be based in San Francisco, CA or New York, NY

Salary: $290,400 - $363,000 USD

Company

Scale AI provides high-quality data and full-stack technologies to power the world's leading AI models for enterprises and governments.

What you will do

• Build, profile, and optimize the internal LLM training and inference framework.
• Collaborate with ML research teams to accelerate the development of next-generation models and data curation.
• Research and integrate state-of-the-art technologies to optimize ML system performance.

Requirements

• Expertise in large-scale distributed ML systems and multi-node LLM training/inference.
• Experience with post-training methods such as RLHF, RLVR, and algorithms like PPO or GRPO.
• Proficiency in CUDA, PyTorch, Transformers, and Flash Attention.
• Strong software engineering skills and ability to operate in a cross-functional team.
• Must be based in San Francisco, CA or New York, NY.

Nice to have

• Demonstrated expertise in instruction tuning, tool use, reasoning, agents, or multimodal LLMs.

Culture & Benefits

• Comprehensive health, dental, and vision coverage.
• Retirement benefits and a learning and development stipend.
• Generous PTO and commuter stipend.
• Equity compensation grants.