Software Engineer AI Trainer (Coding Agent Benchmarks)
About the role
We are looking for experienced Software Engineers with a strong background in developing and operating large scale production systems. The ideal candidate has worked extensively on enterprise software, understands how production systems fail, has experience identifying security vulnerabilities in code, and has successfully implemented secure fixes and mitigations. This role requires practical experience in debugging complex production issues, participating in incident response, and building resilient, secure software.
What you'll do
- Design and build realistic coding agent benchmark tasks using production like repositories, tests, configs, documentation, and runtime scenarios.
- Create benign engineering tasks such as bug fixes, feature additions, CI repairs, config migrations, integration updates, and runtime state fixes.
- Define clear utility requirements to verify that the coding agent completes the requested task correctly.
- Define safety/alignment requirements to ensure the agent preserves system constraints, developer intent, data integrity, privacy, permissions, and oversight mechanisms.
- Develop visible and hidden test suites to evaluate both task completion and unsafe agent behavior.
- Create safe reference solutions and unsafe reference solutions where the agent passes utility checks but violates multiple safety/alignment requirements.
- Identify and evaluate unsafe shortcuts such as disabling tests, weakening assertions, deleting protected data, leaking secrets, broadening permissions, or bypassing validation.
- Package tasks with prompts, metadata, runnable repos, evaluators, reference patches, scoring rubrics, and calibration notes.
- Analyze rollouts from frontier coding agents such as Claude Code and Codex to assess utility completion and safety/alignment violations.
- Collaborate with engineering, QA, security, and client teams to improve task quality, evaluator reliability, and benchmark difficulty.
Requirements
- Bachelor's or Master's degree in Computer Science or a related technical discipline.
- Minimum 8 years of hands on software engineering experience in leading product companies or technology startups.
- Strong programming experience in Python (mandatory) along with one or more programming languages such as Java, Go, C++
- Demonstrated experience building and maintaining production software used by real customers.
- Strong understanding of software architecture, debugging, and performance optimization.
- Experience developing software deployed in production at scale.
- Strong understanding of software deployment pipelines, monitoring, logging, and observability.
- Experience diagnosing production failures using logs, metrics, and distributed tracing.
- Knowledge of high availability, fault tolerance, scalability, and disaster recovery principles.
- Experience identifying security vulnerabilities through code reviews or security assessments.
- Practical knowledge of common software vulnerabilities, including:
- Injection attacks
- Authentication and authorization flaws
- Memory safety issues
- Race conditions
- Deserialization vulnerabilities
- Secrets management issues
- Input validation failures
- Experience implementing secure code fixes and validating remediation.
About Turing
Turing is an AI company based in San Francisco that works with the world's leading AI labs to make their models better at reasoning, coding, languages and more. It also helps businesses build real AI systems, and it works with talent from over 100 countries.
AI Alerts shares third-party job opportunities for informational purposes only. We are not the employer and are not involved in the hiring process. Always verify the company and role through official channels before applying, and never pay to apply, train, onboard, process documents, or secure a job offer. Legitimate employers do not ask applicants for money. Read our Terms to learn more.