AI Researcher, Core ML (Turbo)

📋 Description

• Build and operate high-performance inference and RL/post-training engines.
• Design algorithms, architectures, and scheduling for low latency, high throughput.
• Prototype and maintain inference stacks (SGLang, vLLM, ATLAS-style).
• Profile and optimize GPU, networking, and memory for latency and cost.
• Unify inference with RL/post-training pipelines to improve efficiency.
• Own production systems and drive roadmap across kernel, memory, and APIs.

🎯 Requirements

• 3+ years of experience in ML systems, large-scale training, or inference.
• Advanced degree or equivalent practical experience.
• Strong Python coding and ability to implement production-grade changes.
• Track record of end-to-end technical projects (papers, open source, or production).
• Ability to read RL/post-training papers and translate insights into code.
• Experience with large-scale inference systems or RL/post-training methods.

🎁 Benefits

• Startup equity
• Health insurance
• Other competitive benefits