About Adzzat Adzzat is an applied AI research lab. We turn enterprise data and human expertise into training data and evaluations for frontier AI labs. The role Design and deliver RL environments built from supplied code and domain data. This is an end-to-end, ML-leaning builder role. It is not a pure backend role or a research-only role.
Location:
Mumbai, India Non-negotiable You have created an RL environment, or done real hands-on work on one. Show a runnable repo or inspectable artifact and explain what you built. This matters more to us than your degree or your title.
What you'll do
• Decide which data can become a useful environment 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 reward hacking.
• Run agent experiments and measure whether post-training improves performance.
• Ship containerised, reproducible setups in Docker, in a standard format such as Harbor. Strong skills
• ML and RL fundamentals, including gradient descent and how RL environments work
• Solid recent Python
• Linux, Docker, deployment and sandboxes
• Verifier design that resists gaming
• Training or post-training models is a strong extra signal Ideal profile B.
Tech in Machine Learning or in AI and Data Science. This is a preference, not a filter.
How to apply
Apply with your resume and a link to a runnable repo or artifact. Add one line on what you built. adzzatlabs.com
📌 RL Environment Engineer (Mumbai)
🏢 Adzzat
📍 Mumbai