Research Engineer - Post-training
Magic AIMagic’s mission is to build safe AGI that accelerates humanity’s progress on the world’s most important problems. We believe the most promising path to safe AGI lies in automating research and code generation to improve models and solve alignment more reliably than humans can alone. Our approach combines frontier-scale pre-training, domain-specific RL, ultra-long context, and inference-time compute to achieve this goal.
About the role:
As a Research Engineer in post-training, you'll help develop novel techniques and datasets to maximize model performance for real-world applications, leveraging data and compute at scale. You’ll enable our models to complete engineering, code review, and software design tasks in large, real-world codebases while incorporating cutting-edge reinforcement learning (RL) methods.
What you might work on:
Research and develop innovative post-training techniques and reinforcement learning strategies to enable models to autonomously generate, debug, and optimize software
Build dynamic reward systems and feedback pipelines to align model outputs with human-like decision-making in software development
Scale up synthetic dataset generation and evaluations to drive iterative improvements in autonomous coding and problem-solving tasks
Improve model capabilities for generating substantial, high-quality, functional code
Design scalable approaches for evaluations and synthetic dataset generation that align with reinforcement learning objectives
Explore and implement novel methods to align AI behavior with human intent, ensuring reliability and performance in high-stakes environments
What we’re looking for:
Strong experience deploying and fine-tuning LLMs for real-world applications.
Strong general software engineering skills
Thorough knowledge of the deep learning literature
Expertise in reinforcement learning techniques such as actor-critic, self-play or self-evaluation, or RLHF
Ability to come up with and evaluate novel research ideas
Obsession with details, reliability, and good testing to ensure data quality and integrity
Willingness to dive deeply into a large ML codebase to debug
Passion for building systems that redefine software engineering through fully autonomous AI
Magic strives to be the place where high-potential individuals can do their best work. We value quick learning and grit just as much as skill and experience.
Our culture:
Integrity. Words and actions should be aligned
Hands-on. At Magic, everyone is building
Teamwork. We move as one team, not N individuals
Focus. Safely deploy AGI. Everything else is noise
Quality. Magic should feel like magic
Compensation, benefits and perks (US):
Annual salary range: $100K - $550K
Equity is a significant part of total compensation, in addition to salary
401(k) plan with 6% salary matching
Generous health, dental and vision insurance for you and your dependents
Unlimited paid time off
Visa sponsorship and relocation stipend to bring you to SF, if possible
A small, fast-paced, highly focused team