AI Engineer​/Generative AI Engineer Agentic AI,AWS Bedrock AgentCore,Claude Agent SDK,Langfuse Los

• Contract

Duration: 3+ Months (Extension Possible)

Specialisation:
Agentic AI, AWS Bedrock Agent Core, Claude Agent SDK, Langfuse, AI Observability & Evaluation

Job Summary

We are seeking an experienced AI Engineer with strong hands‑on expertise in building, deploying, and monitoring production‑grade AI agents and Generative AI solutions using AWS technologies.

The ideal candidate will have experience developing AI agents using Claude Agent SDK
, deploying them on Amazon Bedrock Agent Core Runtime
, automating deployments through Git Hub Actions
, and implementing Langfuse for observability and continuous evaluation of agent traffic
.

The role requires a strong combination of AI engineering, cloud deployment, data pipeline development, and LLM performance monitoring.

Key Responsibilities

1. Agentic AI Development

• Design, develop, and deploy AI agents using Claude Agent SDK and Python.
• Build intelligent, autonomous agents capable of executing complex workflows and interacting with external tools, APIs, and knowledge bases.
• Develop agent orchestration workflows with appropriate error handling, retry mechanisms, and guardrails.
• Integrate AI agents with enterprise applications and data sources.

2. AWS Bedrock & Agent Core

• Deploy and manage AI agents using Amazon Bedrock Agent Core Runtime.
• Develop scalable, secure, and production‑ready agent architectures on AWS.
• Integrate agents with Amazon Bedrock foundation models and enterprise knowledge bases.
• Implement agent authentication, access controls, logging, and runtime monitoring.

3. Langfuse Deployment & AI Observability

• Deploy, configure, and maintain Langfuse for comprehensive LLM and agent observability.
• Integrate Langfuse with AI agents to capture traces, prompts, responses, tool calls, and execution metrics.
• Monitor agent performance, response latency, token consumption, and operational costs.
• Identify and troubleshoot production issues through distributed tracing and monitoring dashboards.
• Design and implement continuous evaluation frameworks for production AI agent traffic.
• Evaluate agent responses for accuracy, relevance, hallucinations, task completion, and tool execution quality.
• Develop automated evaluation pipelines using Langfuse, LLM-as-a-Judge, and custom evaluation metrics.
• Implement continuous feedback mechanisms to improve agent reliability and effectiveness.
• Establish quality benchmarks and detect agent performance regressions.
• Develop AWS Step Functions workflows integrating Amazon Textract and Amazon Comprehend for intelligent document processing.
• Build document ingestion, preprocessing, and data transformation pipelines.
• Implement vector database solutions, including document chunking, embedding generation, and vector indexing.
• Integrate AI agents with Retrieval-Augmented Generation (RAG) pipelines and enterprise knowledge bases.
• Optimize retrieval performance and contextual accuracy.

6. CI/CD & Deployment Automation

• Build and maintain CI/CD pipelines using Git Hub Actions.
• Automate agent code builds, testing, deployment, and configuration management.
• Implement deployment workflows for Amazon Bedrock Agent Core Runtime.
• Integrate automated agent evaluations into CI/CD processes.
• Apply Dev Ops best practices for version control, release management, and production monitoring.

Required Technical Skills

• Evaluation: Continuous agent evaluation, LLM-as-a-Judge, evaluation metrics and automated testing.
• RAG: Vector databases, embeddings, chunking strategies, indexing, knowledge base integrations.
• Cloud: AWS architecture, IAM, Cloud Watch, security, and deployment practices.

Good-to-Have Skills

• Experience with Lang Chain, Lang Graph, or other agent orchestration frameworks.
• Experience with RAGAS, Deep Eval, or similar LLM evaluation frameworks.
• Familiarity…