Member of Technical Staff

• We’re hiring a Member of Technical Staff to own the design, development, and production of Frontier Data Products
• You’ll build the sandboxed, reproducible environments AI agents rely on during training and evaluation, the terminals, browsers, and tool-augmented workspaces they operate inside
• This is a hands-on engineering role. You’ll write production-quality infrastructure, integrate with the broader RL tooling ecosystem, and partner closely with our data operations team to keep environments robust and observable for annotators and model agents alike
• Above all, you’ll need a real grasp of how RL training loops consume environments and where they tend to break
• Design, build, and maintain sandboxed RL environments for agentic AI training—including terminal emulators, browser automation harnesses, computer-use simulators, and tool-augmented workspaces (e.g., environments built on frameworks like TerminalBench, OSWorld, and Tau-bench)
• Develop reproducible, containerized execution environments (Docker, VMs, lightweight sandboxes) that support deterministic task rollouts and reward signal collection
• Integrate with and extend open-source agentic tooling and custom CLI/API harnesses to enable multi-step agent interaction
• Build instrumentation and observability layers- structured logging, trajectory capture, state snapshotting, so training runs and human annotation sessions produce clean, auditable data
• Collaborate with data operations to design task curricula and evaluation protocols that stress-test model capabilities across environment types
• Own environment deployment and reliability: CI/CD pipelines, automated testing of environment configurations, and monitoring for drift or breakage across versions
• Rapidly prototype new environment types as client and internal requirements evolve, moving from spec to working system in days, not weeks
• Reinforcement learning has become the state-of-the-art approach for training agentic AI, and environment quality is one of its biggest bottlenecks
• Environments that are brittle, non-deterministic, or poorly instrumented produce noisy signals that directly degrade model performance. You’ll be solving one of the highest-leverage infrastructure problems in AI today
• You’ll work across a portfolio of projects spanning different AI labs and model capabilities with no single-product monotony. The environment types you build will evolve as RL continues to shape the frontier of agent capabilities
• Alignerr is a small, high-impact team inside Labelbox. You’ll have startup-level ownership with growth-stage resources

Benefits

• Flexible vacation policy (we don’t count PTO Days)
• 401k Program
• College savings account
• HSA
• Daily lunches paid for by the company (especially convenient while working from home)
• Virtual wellness and guided meditation programs
• Dog-friendly office
• Regular company social events (happy hours, off-sites)
• Professional development benefits and resources
• Remote friendly (we hire in-office and remote employees)

• Strong debugging instincts, you can trace failures across process boundaries, container layers, and network calls
• Experience building or maintaining developer tooling, CLI tools, or infrastructure automation
• 2+ years of professional software engineering experience, with strong fundamentals in Python and at least one systems-level language (Go, Rust, C++)
• Ability to read and implement from academic papers and open-source benchmark repositories without extensive hand-holding
• Demonstrated experience with containerization and sandboxing (Docker, Podman, Firecracker, or similar) in production or near-production contexts
• Comfort working with browser automation frameworks or terminal interaction tooling
• Familiarity with RL concepts: MDPs, reward shaping, episode structure, observation/action spaces. You don’t need to have trained models, but you need to understand what an environment must provide to an RL training loop
• The ideal candidate is a strong software engineer first, with genuine curiosity and working knowledge of how modern AI systems are built and evaluated
• You’re the kind of engineer who reads a benchmark paper or evaluation framework and immediately thinks about how to make the underlying system more robust, not just how to improve the model’s output
• You thrive in ambiguity. You can take a loosely defined project requirement, “build an environment that tests an agent’s ability to navigate a file system and execute multi-step bash workflows” and deliver a working, tested, documented system without needing a detailed spec
• You move fast, but you care about reliability because you know systems that break silently poison the data everything downstream depends on
• You’ve probably built infrastructure or developer tooling at a startup or mid-stage company, and you’ve been pulled toward the AI space maybe through side projects, open-source contributions, or a prior role adjacent to an applied AI or ML team
• Direct experience building or contributing to RL environments (Gymnasium/Gym, PettingZoo, or custom environment implementations)
• Experience with agentic AI evaluation frameworks (SWE-bench, WebArena, OSWorld, TerminalBench, or similar)
• Familiarity with GCP or AWS infrastructure (Compute Engine, ECS/EKS, Cloud Build)
• Prior work at an AI data company, ML platform company, or AI research lab
• Contributions to open-source projects in the RL, agents, or dev-tools space