SWE (RL Environments) "Reinforcement Learning"

San Francisco, United States | Posted on 06/15/2026 AI Talent Now, LLC is a powerhouse in direct‑hire talent acquisition, connecting exceptional talent with industry‑leading organizations across IT, Engineering, Financial Services & Fintech, and Manufacturing & Robotics. Headquartered in Atlanta, Georgia, we serve clients and candidates nationwide. Job Description AI Talent Now Job #ZR 72 About us This dynamic company is helping push the frontier of LLMs and AI Agents through novel datasets and experimentation. We build the most complex infrastructure that powers frontier data creation for agentic and hard‑reasoning workflows. Working with all five leading AI labs, we are becoming the go‑to partner for data infrastructure for YC companies. Our sharp hockey‑stick growth and talent density come from a founding team with backgrounds in top IB and quant firms. We build the training data and evaluation infrastructure that frontier AI labs use to improve their models. Working with the world's leading labs, we design high‑signal datasets and run rigorous evaluations that go beyond static benchmarks. At a small, early post‑Series A team, individual contributors directly influence how the next generation of models learn and improve. As an RL Environment Engineer you will design datasets that directly influence how frontier models learn and work hands‑on with research teams at top AI labs. Responsibilities Design and develop datasets that shape frontier model learning. Collaborate with research teams at leading AI labs to build and refine reinforcement learning environments. Implement high‑quality benchmarks and evaluate model performance beyond static tests. Qualifications Recent graduates from top schools focused on excellence and depth; extensive track record not required. First‑author publications at top venues such as NeurIPS or ICML are highly desirable. Open to profiles from data companies with benchmarking experience. Ideal candidates have created iconic benchmarks and possess experience in supervised fine‑tuning (SFT) or reinforcement learning (RL). Experience 1–6 years of experience as a software engineer. Explicit experience building reinforcement learning environments. Signals of excellence in software engineering (e.g., work at an RL company, top VC‑backed startup, strong side projects, quant or hedge‑fund background, or founding/early‑stage startup engineer). CS degree from a top‑30 school (US/CA/EUR only). Strong full‑stack skills with depth in Python, Typescript, and other backend languages. Developed quantitative frameworks for measuring dataset quality/diversity. Bias for action and execution; willing to tackle difficult and tedious work. Compensation and Logistics Base salary: $150k–$250k, with significant bonus potential based on performance. Bonuses are uncapped and can substantially increase total compensation. Visa sponsorships are possible (experience in H1B and other types). Work Arrangement Flexible working hours; most team members in the office from noon to midnight. Work environment encourages results over strict hours. EEO Statement We are an equal opportunity employer and welcome applications from all qualified individuals regardless of race, color, religion, sex, gender identity, sexual orientation, national origin, disability, or veteran status. #J-18808-Ljbffr AI Talent Now