Hiring: AI Engineer | Agentic AI, AWS Bedrock AgentCore & Langfuse | 15+ Years

Description

The role is titled AI Engineer or Generative AI Engineer.

The team is hiring a hands-on AI engineer to build, deploy, monitor and keep improving production AI agents, working with Python, agentic AI, AWS Bedrock AgentCore and LLM evaluation.

Responsibilities

• Write AI agents in Python on top of the Claude Agent SDK.
• Ship agents to AWS Bedrock AgentCore Runtime.
• Create golden datasets and build LLM-as-a-Judge evaluations.
• Make automated evaluations act as quality gates inside CI/CD pipelines.
• Set up Langfuse/OpenTelemetry for AI observability and tracing.
• Measure agent accuracy, task completion, tool execution and performance.
• Assist with RAG pipelines and AWS data processing workflows.

Requirements

• Python and agentic AI development.
• AWS Bedrock AgentCore Evaluations or Bedrock evaluation.
• Golden-dataset design and curation.
• Designing LLM-as-a-Judge and calibrating it against human labels.
• Automated evaluation and CI gate integration.
• Langfuse and/or OpenTelemetry.
• 6 to 8+ years in software engineering, cloud engineering, or AI/ML.
• Hands-on experience with production AI agents and continuous evaluation.
• Strong problem-solving and troubleshooting skills.
• Good to have: RAGAS or equivalent evaluation frameworks.
• Good to have: trajectory evaluation and agentic red-teaming.
• Good to have: Bedrock Guardrails, Strands Agents SDK and GitHub Actions.

Conditions

Contract length is 3+ months, with an extension possible.

Listed experience is 15+ years.

Candidate information is kept confidential under EEO guidelines.