Description

You will design and implement complex multi-step reasoning chains and agentic RAG pipelines using LangGraph and structured output patterns.

This role is on-site.

Responsibilities

• Architect and enforce safeguard mechanisms including prompt injection defense, hallucination mitigation, and context-window management across AI agents.
• Integrate AI components with Model Context Protocol (MCP) to enable agents to access a shared, grounded knowledge base with reliable and auditable outputs.
• Collaborate with Germany-based AETHER teams to embed AI services into CI/CD pipelines, ensuring seamless deployment, observability, and compliance with EU AI Act and DORA requirements.
• Continuously evaluate and optimize prompt strategies, retrieval mechanisms, and model configurations to improve accuracy, latency, and reliability at enterprise scale.

Required Skills

• 5+ years of hands-on experience building production AI/ML systems.
• Expertise in LLM and Retrieval-Augmented Generation (RAG) development for production applications.
• Proficiency in LangGraph-based agentic RAG pipeline design and structured output patterns.
• Strong Python skills for building and operating production AI/ML systems.
• Experience with CI/CD integration, containerization, and orchestration using Docker and Kubernetes.

Preferred Skills

• AI/ML experience in regulated environments and familiarity with EU AI Act and DORA requirements.
• Experience with GCP, DevSecOps practices, and GitHub Actions for enterprise delivery workflows.

Key Skills

Education

Any Graduate