Founding RL Engineer — Build Frontier AI Environments

S27a; San Mateo (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Deccan AI is seeking a founding engineer to design and build reinforcement-learning environments, evaluation harnesses, and feedback systems that support frontier AI labs and sophisticated customers. You will bridge research ambiguity to concrete environments, writing robust, scalable code and technical docs.

The role emphasizes moving from prototype to production, enabling repeatable RL workflows, and shaping Deccan's RL practice with high-ambition, hands-on engineering ownership.

Qualifications

• Proven experience with reinforcement learning and evaluation workflows.
• Strong programming and systems design skills.
• Ability to work with researchers and customers to translate requirements into deployable systems.

Responsibilities

• Design and build RL environments, task suites, evaluation harnesses, and feedback systems for frontier AI workflows.
• Translate ambiguous research or customer needs into concrete technical specs and data requirements.
• Prototype quickly, then harden reusable infrastructure for production use.

Skills

Reinforcement learning

Python

ML systems

Documentation

Education

BS in CS or related

Tools

PyTorch

JAX

TensorFlow

Git

Job description

Deccan AI is seeking a founding engineer to design and build reinforcement-learning environments, evaluation harnesses, and feedback systems that support frontier AI labs and sophisticated customers. You will bridge research ambiguity to concrete environments, writing robust, scalable code and technical docs.

The role emphasizes moving from prototype to production, enabling repeatable RL workflows, and shaping Deccan's RL practice with high-ambition, hands-on engineering ownership.