Senior ML/Evaluation Engineer
Primary stack
Nice to have's
Job description
About the Position
We are building an Enterprise Agent Development Platform, a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The platform standardizes agent development across the organization. The initiative spans agent framework design, runtime architecture, marketplace integration, CI/CD automation, and enterprise-grade observability, reducing agent development from months to days while enforcing consistent security, quality, and governance standards.
Responsibilities
- AWS AgentCore Evaluation (on-demand mode for CI/CD gates, online mode for production sampling)
- LLM-as-judge evaluator design (built-in AgentCore evaluators - helpfulness, correctness)
- Custom code-based Lambda evaluators (Python - deterministic checks)
- Evaluation levels (TRACE for per-response, TOOL_CALL for per-invocation, SESSION for workflow)
- OTel spans from AWS AgentCore Observability as evaluation input
- Enterprise evaluation standard authoring (mandatory dimensions, pass/fail criteria)
Requirements
- 5+ years ML engineering or AI platform engineering
- LLM evaluation framework design and implementation
- Custom evaluator implementation for deterministic quality checks
- CI/CD deployment gate design for ML model or agent quality
Nice to Have
- AWS AgentCore Evaluation API hands-on (CreateEvaluation, GetEvaluationResult)
- AWS Bedrock Guardrails for PII detection evaluator integration
- CloudWatch metrics output from AgentCore Evaluation for online mode
We Offer
- Opportunity to work on cutting-edge AI projects
- Remote work options in Czech Republic or Slovakia
- Competitive contractor compensation
About the Company
EPAM Systems is a global software engineering and product development company, delivering digital platforms and large-scale systems for the world's leading organizations.
© EPAM. This job description was sourced from the employer's public career page. TheJob is not the employer — we index the posting and route candidates to the source. All content rights and hiring decisions belong to the employer.
EPAM helps organizations innovate their business processes and rethink the way they manage their businesses so they can remain competitive in this new digital age.