Software Engineer, Multi-agent
As a senior software engineer on the multi-agent team, you will help the multi-agent team make major advances in the areas of deep reinforcement learning, specifically AI-generating algorithms, multiple interacting agents (https://openai.com/blog/emergent-tool-use
), open-ended algorithms, and automatically generating training environments. You will take a major role in building the environments in Unity that our team’s experiments are conducted in and conduct RL experiments to validate the improvements to the domains. Machine learning experience is a strong plus, but is not required.
We expect you to have:
Strong knowledge of software architecture and systems design.Experience with the Unity engine, including knowledge of the following components: 3D geometry and math (Euclidean vectors, quaternions, trigonometry, etc.); Physics simulation (mechanics and stabilization techniques); Custom Editor tools framework; General performance tuning and debuggingExperience building and deploying a distributed system in the cloud.The ability to autonomously solve complex engineering challenges given high-level feedback.Interest in the research focus of the team (building simulators for multi-agent RL).Desire to join a team and work towards an ambitious, common research goal we collectively find interestingGood communication and collaboration skillsComfortable working on large, internal codebases with the team & organization.A desire to contribute to team goals in any way possible, including learning new technical skills to do so.
Nice to have:
Experience working on a small development team Experience with Machine-Learning or Reinforcement-Learning experimentation, ideally at a scale greater than single-machine.Strong knowledge of Unity debugging, with experience using the Unity Profiler, Unity Frame & Physics Debuggers and other technical debug tools.Strong knowledge of server infrastructures, with experience deploying service applications to clients or customers.Experience coding in Python.A passion for the research areas of focus of the team and/or learning about the research interests of the team>5 years in industry (video games or something else using the Unity engine).
We’re building safe Artificial General Intelligence (AGI), and ensuring it leads to a good outcome for humans. We believe that unreasonably great results are best delivered by a highly creative group working in concert. We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.
This position is subject to a background check for any convictions directly related to its duties and responsibilities. Only job-related convictions will be considered and will not automatically disqualify the candidate. Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.
Health, dental, and vision insurance for you and your family
Unlimited time off (we encourage 4+ weeks per year)
Flexible work hours
Lunch and dinner each day