Reinforcement Learning Environment Engineer

Kindredventures; San Francisco (CA); On-site; USD 140,000 - 220,000; Full time

Job summary

Mecka AI is building the data infrastructure layer for robotics and embodied AI, designing and operating global systems for data capture, labeling, and workflows used by leading AI labs and robotics companies. The Research Engineer, RL Env role focuses on constructing reinforcement learning environments, writing working software, and running experiments to understand model capabilities.

You will collaborate with researchers, engineers, and product teams to translate real tasks into computable

Qualifications

• Hands-on experience formulating RL problems, constructing environments, training agents.
• Strong programming and debugging skills to build reusable research systems.
• Solid experimental design and statistical reasoning for controlled comparisons.
• Ability to reason about environment dynamics, reward design and agent behavior.
• Independent research judgment and clear communication.

Responsibilities

• Build environments: Define tasks, observations, actions and state transitions; implement reset, termination, and measurable outcomes.
• Develop rewards and scoring: Translate objectives into feedback and evaluation criteria.
• Run learning experiments: Implement baseline agents, train and compare policies, design controlled experiments.
• Make evaluation reliable: Separate training and held-out tasks, check leakage, report uncertainty.
• Investigate failures: Inspect trajectories to distinguish policy limits from data/reward/environment issues.
• Build with the team: Validate task assumptions with domain experts and turn prototypes into reusable tools.

Skills

RL environment

Programming skills

Experimental design

Statistical reasoning

Communication

Job description

Mecka AI is building the data infrastructure layer for robotics and embodied AI, designing and operating global systems for data capture, labeling, and workflows used by leading AI labs and robotics companies. The Research Engineer, RL Env role focuses on constructing reinforcement learning environments, writing working software, and running experiments to understand model capabilities.

You will collaborate with researchers, engineers, and product teams to translate real tasks into computable