Job Description
Looking for engineers with experience in small, fast-paced teams where individuals own large parts of the product. Strong command of at least one major backend-focused stack: TypeScript, Python, Go, or Java , with bonus points for TypeScript proficiency is required. You'll be expected to build and maintain RL environments and sandbox systems that help train advanced coding agents used by top AI labs. You will rapidly onboard to new codebases (every 4–6 weeks), develop a strong understanding, and design RL tasks and scenarios around them. You'll also build internal tools, utilities, and frameworks that enable the environment team to prototype and iterate significantly faster.
About Respond
This role is for one of our clients in the Insurance Industry.