Adzzat is an applied AI data company building the human layer behind frontier AI
- high-quality data annotation, evaluation benchmarks and RL environments for AI labs and robotics companies. Our teams work on the problems models actually fail at: robotics grasping, agent behavior, edge-case judgment. We're a young Mumbai team hiring people who want to shape how AI learns, not just watch it happen.
Job Description
Adzzat is an applied AI research lab that turns enterprise data and human expertise into training data and evaluations for frontier AI labs.
Location:
Mumbai, India (onsite) Compensation: ₹15-20 LPA + ESOPs Lead the design and delivery of RL environments built from supplied code and domain data. An end-to-end, ML-leaning builder role, not a pure backend or research-only role.
What you'll do
Decide which data can become a helpful setting and clarify what data a lab needs. Work backwards from existing benchmarks,
or design suitable evaluations. Build rewards, graders and verifiers that score agent runs and resist shortcuts and rewards hacking. Run agent experiments and measure whether post-training improves performance. Ship containerised, reproducible setups in Docker, in a standard format such as Harbor. Learn more: adzzatlabs.com Non-negotiable You have personally built at least one RL environment. Show a runnable repo or inspectable artefact and explain what you built. Strong skills ML and RL fundamentals (including gradient descent and how RL environments work); strong recent Python; Linux, Docker, deployment and sandboxes; verifier design that resists gaming. Training or post-training models is a strong extra signal.
📌 Lead RL Environment Engineer (Mumbai)
🏢 Adzzat
📍 Mumbai