Staff Software Engineer, RL Environments
$252k - $315k • Remote • San Francisco, CA; New York, NY
Posted 5d ago
Job Location
San Francisco, CA; New York, NY
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
Scale AI is seeking a Staff Software Engineer to own the technical foundation for building, running, verifying, and delivering Reinforcement Learning (RL) environments at scale. This role involves designing the platform for sandboxed execution, environment packaging, rollout orchestration, and verifier frameworks, while also diving deep into instrumenting real applications, designing task suites, and building robust graders. This is a hands-on engineering position requiring technical leadership across multiple teams and the ability to write complex code.
Responsibilities
- Own the technical foundation for building, running, verifying, and delivering RL environments at scale.
- Design the platform for sandboxed execution, environment packaging and versioning, rollout orchestration, trajectory capture, verifier frameworks, and authoring surfaces.
- Instrument real applications, design task suites to expose capability gaps, and build graders for adversarial optimization.
- Set technical direction across multiple teams and write complex code.
- Translate research goals into production systems.
- Build internal tools that non-engineers rely on daily.
Requirements
- 8+ years of software engineering experience with strong fundamentals in distributed systems, system design, data structures, and algorithms.
- Strong Python skills and a track record of shipping production software.
- Comfort in at least one other part of the stack (TypeScript/React, Go, Rust, or similar).
- Deep experience with containerization and sandboxed execution (Docker, VMs, gVisor/Firecracker, Kubernetes, or equivalent).
- Experience building or operating high-throughput backend systems (orchestration, job scheduling, queuing, large-scale data pipelines).
- Hands-on experience building with LLMs including agent loops, tool calling, MCP, or eval harnesses.
- Demonstrated ability to own ambiguous, undefined problems end to end and drive them to a shipped system.
- Excellent written and verbal communication skills.
Benefits
- Base salary
- Equity
- Comprehensive health, dental and vision coverage
- Retirement benefit