AI is here to stay and our client has created an AI-powered development platform designed to enhance team productivity by providing context-aware assistance throughout the coding process. Their strong belief is that software should enhance developers, not replace them. It deeply understands large, complex codebases, enabling it to offer relevant code completions, suggest edits, and facilitate efficient collaboration among developers.

We’re looking for a Research Scientist to lead the design and execution of large-scale reinforcement learning (RL) experiments aimed at enhancing AI coding agents. This role is ideal for someone with deep expertise in post-training large language models (LLMs) and a proven track record of driving impactful research projects from concept to deployment.

What You’ll Do

• Conduct cutting-edge research to advance the capabilities of code-generating agents
• Design and scale large RL experiments for fine-tuning and post-training LLMs
• Collaborate with a cross-functional team of researchers and engineers to shape research priorities
• Provide technical leadership and mentorship to junior researchers and research residents
• Stay current with the latest developments in RL, LLMs, and software engineering

What We’re Looking For

• 2+ years of hands-on experience developing and scaling RL algorithms for post-training LLMs
• Demonstrated leadership and individual contributions to successful LLM projects
• Strong coding skills and a deep understanding of RL fundamentals
• Excellent problem-solving abilities and comfort working both independently and in a team

Bonus Points For

• Experience in LLM post-training specifically for software engineering tasks
• PhD in Computer Science or a related field
• Strong publication record in top-tier ML/AI conferences and journals

Benefits

• Flexible work hours
• Competitive salary & equity
• Annual tools stipend
• Comprehensive health, dental, vision, and life insurance
• Short- and long-term disability coverage
• Unlimited paid time off + holidays — we value trust, ownership, and outcomes
• Frequent team events and company socials