Platform Engineer, RL & Eval Data
New
A
Anyone AIAI data platforms
Argentina - Fully RemoteFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Fluent English.
- Experience
- 5+ years in software, data or ML engineering
- Required Skills
- DockerPostgreSQLPythonKubernetesTypeScriptReactDistributed Systems
Requirements
- Bring 5+ years of experience in software, data or ML engineering.
- Have recent work in AI/ML data, model evaluation, annotation or developer tooling.
- Demonstrate a track record of running and maintaining production systems.
- Write clean, tested and maintainable backend code in Python.
- Have experience designing APIs and the data models behind them.
- Know relational databases such as Postgres, including schema design, migrations and query performance.
- Use TypeScript and React to build and maintain internal tools.
- Design distributed systems for many concurrent long-running jobs, including orchestration, queues, retries and failure recovery.
- Have experience with containers and container orchestration, a major cloud provider, observability and security fundamentals.
- Have hands-on experience building RL environments for LLM agents and running agent code in isolated sandboxes at scale.
- Have experience building or running LLM evaluation harnesses or benchmarks, and writing verifiers, graders or reward functions.
- Have experience building annotation, labeling or human-data tooling and contributor or reviewer workflows.
- Use AI coding agents carefully, work independently, take initiative and communicate clearly in writing with technical and non-technical colleagues.
- Be fluent in English.
Responsibilities
- Maintain production platforms by fixing bugs, reducing technical debt, and improving test coverage and documentation.
- Design and ship platform features across databases, backends, APIs and internal tools.
- Scale systems to handle larger workloads with predictable performance and cost.
- Build RL environments and infrastructure, including sandboxes, environment images, rollouts and reward computation.
- Maintain reliability and security through monitoring, alerting, incident response, access control and protection of client data.
- Build tools for task authors, reviewers and project leads, and help produce fast-turnaround samples when needed.
View Full Description & ApplyYou'll be redirected to the employer's site
