Full-Stack RL Engineer — Shape AI Training Data & Tools

HUD; Singapore; On-site; SGD 192,000 - 269,000; Full time

Benefits offered by this job

Competitive compensation

Medical, dental, and vision coverage

Lunch and dinner in the office

Equinox membership

401k

Commuter benefits

Job summary

HUD is seeking a Full-Stack Software Engineer, Reinforcement Learning to build product surfaces, backend systems, and internal tools powering HUD’s RL data engine. You’ll own product surfaces end-to-end, including backend services, APIs, databases, dashboards, tools, vendor workflows, data collection, and observability for RL rollouts.

You don’t need to be a researcher, but you will collaborate with research engineers and vendors to translate ambiguous needs into polished products that enable

Qualifications

• Strong software engineering fundamentals and full-stack experience.
• Proficiency in Python and modern web stack (React/TypeScript).
• Ability to translate ambiguous needs into polished products for RL systems.
• Experience with cloud, CI/CD, observability, and production debugging.
• Excellent cross-functional communication across research, engineering, operations, and vendors.

Responsibilities

• Develop product-facing tools for browsing environments, inspecting trajectories, reviewing task quality, debugging failures, and understanding model behavior
• Build vendor-facing workflows that make it easy for external partners to create, submit, test, and iterate on RL environments and training data
• Create dashboards and observability tools that surface environment quality, eval results, data collection progress, grader issues, reward signal problems, and pipeline health
• Design backend services and APIs that connect task authoring, data collection, evaluation, QA/QC, and RL training infrastructure
• Partner closely with research, operations, and GTM teams to turn vague, high-stakes requests into well-designed systems that ship quickly

Skills

Python

React

TypeScript

Full-stack

Observability

CI/CD

Cloud

Communication

Tools

AWS

Kubernetes

Terraform

Docker

Grafana

Job description

HUD is seeking a Full-Stack Software Engineer, Reinforcement Learning to build product surfaces, backend systems, and internal tools powering HUD’s RL data engine. You’ll own product surfaces end-to-end, including backend services, APIs, databases, dashboards, tools, vendor workflows, data collection, and observability for RL rollouts.

You don’t need to be a researcher, but you will collaborate with research engineers and vendors to translate ambiguous needs into polished products that enable