Remote RL Research Engineer: Environments & Pipelines

Remotebridge; United States; Remote; USD 200,000 - 300,000; Full time

Benefits offered by this job

Equity compensation

Remote-first workforce

Health insurance reimbursement

Job summary

micro1 is seeking a Research Engineer to operate at the frontier of Reinforcement Learning, developing environments, training pipelines, and evaluation systems that advance AI models. The role sits at the intersection of research and production, translating experimental ideas into scalable, high-performance systems in a remote-first, fast-paced environment.

Responsibilities include building RL environments, scaling MCPs, synthetic data generation, automated evaluation, and benchmarking using

Qualifications

• Deep experience in Reinforcement Learning and environment design.
• Proven ability to build and scale RL systems and experimentation frameworks.
• Experience in automated data generation and synthetic data pipelines.
• Familiarity with automated evaluation, model validation, and QA workflows.
• Strong written and verbal communication in a collaborative, fast-paced setting.

Responsibilities

• Architect self-contained RL environments with reward functions and evaluators.
• Design and scale episode pipelines and multi-component training processes.
• Build automated data generation systems using synthetic data.
• Develop AI-driven evaluation and quality assurance systems.
• Fine-tune and evaluate open-source RL models with internal data.
• Establish benchmarking frameworks to measure model capability.

Skills

Reinforcement Learning

Environment design

Training pipelines

Automation & data generation

Evaluation systems

Open-source model fine-tuning

Technical writing

Collaboration

Tools

Benchmark frameworks

Open-source RL toolchains

Job description

micro1 is seeking a Research Engineer to operate at the frontier of Reinforcement Learning, developing environments, training pipelines, and evaluation systems that advance AI models. The role sits at the intersection of research and production, translating experimental ideas into scalable, high-performance systems in a remote-first, fast-paced environment.

Responsibilities include building RL environments, scaling MCPs, synthetic data generation, automated evaluation, and benchmarking using