Senior Software Engineer - Agent Evaluation
New
M
MindriftAI Systems Evaluation
Open to candidates in the North America, South America, Asia and Europe.ContractSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- English (B2+ proficiency)
- Experience
- 5+ years
- Required Skills
- DockerPythonJavascriptKafkaTypeScriptFastAPIPostgresRedisReact
Requirements
- 5+ years of professional software development experience.
- Proficiency with Python and FastAPI.
- Proficiency with JavaScript/TypeScript and React.
- Experience with Docker, Postgres, Kafka, and Redis.
- Strong experience writing functional and integration tests.
- B2+ level English proficiency.
- Ability to complete a technical assessment.
- Willingness to undergo identity verification and a background check.
- Ability to use Discord for project communication.
- Reliable internet connection for remote work.
Responsibilities
- Build realistic developer environments featuring codebases, infrastructure, and historical context.
- Design complex tasks and prompts for AI agents based on simulated environment states.
- Define clear, solvable evaluation criteria for agent-driven tasks.
- Write robust tests to verify agent solutions and handle various valid coding approaches.
- Review agent performance, analyze failures, and iterate on task quality based on QA feedback.
View Full Description & ApplyYou'll be redirected to the employer's site
