RL Research Engineer: Build Environments & Experiments

Mecka; New York (NY); On-site; USD 170,000 - 300,000; Full time

Job summary

Mecka AI is seeking a Research Engineer, RL Env to build reinforcement learning environments and support researchers in training models. You will translate real tasks into computable environments, implement tasks, and work with product colleagues and domain experts to turn prototypes into reusable components.

The role emphasizes hands-on software development, identifying failures, and designing methods with the team to advance embodied AI research.

Qualifications

• Hands-on experience formulating RL problems and building environments.
• Ability to train agents and assess results critically.
• Strong programming and debugging skills for research systems.
• Experience with experimental design and statistics.

Responsibilities

• Build environments: define tasks, observations, actions and state transitions; implement reset, termination, and outcomes.
• Develop rewards and scoring; test for exploitation vs. task intent.
• Run learning experiments: implement baseline agents; train and compare policies; design controlled experiments.
• Make evaluation reliable: separate training and held-out tasks; report uncertainty and performance.
• Investigate failures: inspect trajectories and behavior to identify causes; prioritize next steps.
• Build with the team: validate assumptions and turn prototypes into reusable tools.

Skills

RL env design

Programming

Debugging

Experimental design

Communication

Independent research

Job description

Mecka AI is seeking a Research Engineer, RL Env to build reinforcement learning environments and support researchers in training models. You will translate real tasks into computable environments, implement tasks, and work with product colleagues and domain experts to turn prototypes into reusable components.

The role emphasizes hands-on software development, identifying failures, and designing methods with the team to advance embodied AI research.