About this role
AfterQuery in San Francisco is seeking a full-time Software Engineer focused on reinforcement learning environments to design simulations and data that influence how frontier AI models learn. This role suits engineers experienced in containerization and reinforcement learning who want to build core infrastructure for leading AI labs.
Role Overview
The Software Engineer for RL Environments will design the simulations, data, and evaluations that directly shape frontier model learning. Working alongside top AI labs, the professional in this position will experiment with environment design, pilot novel data creation strategies, diagnose failure modes, and develop metrics to measure model improvements. The daily responsibilities include building reward signals, developing quantitative frameworks for dataset quality, and collaborating with researchers to scale training infrastructure.
Key Responsibilities
Requirements
Nice to Have
Skills and Tools
Salary and Benefits
About the Company
AfterQuery is an applied research lab based in San Francisco that curates data solutions for foundation model development. The company serves frontier AI labs with the mission of delivering high-quality data to power advanced models. Backed by investors such as Altos Ventures, BoxGroup, and Y Combinator, along with prominent angels from leading AI organizations, AfterQuery sits directly in the loop of how foundational AI systems improve.
How to Apply
Interested candidates should visit the official AfterQuery careers page to submit an application for this role.
Skills and tech stack
Questions candidates ask
What is the location and work type of this role?
This is a full-time position based on-site in San Francisco, California.
What is the salary range for the Software Engineer position?
The annual salary ranges from $260,000 to $290,000 USD, accompanied by meaningful equity.
What technical skills are required?
Candidates must have experience with Docker or similar containerization tools and a strong familiarity with common reinforcement learning algorithms, particularly regarding the post-training of large language models.
What benefits are provided to eligible employees?
Eligible employees receive health insurance (medical, vision, and dental), a 401(k) with employer match, a daily UberEats meal stipend, and a monthly wellness stipend.
What does AfterQuery do?
AfterQuery is an applied research lab that curates data solutions and builds infrastructure for foundation model development, serving frontier AI labs.