Middle AI Engineer (Agentic AI & RAG Systems)

About the role

A company is looking for a mid-senior AI engineer fluent in English to build, integrate and evaluate agentic AI and RAG systems for an AI testing and evaluation platform. The role centres on production-grade AI application engineering, agent reliability, safety, guardrails and AI risk evaluation, working with product and customer delivery teams to improve AI evaluation capabilities.

Key responsibilities

• Design, build and integrate agentic AI systems into the AI evaluation platform.
• Develop agent harnesses, guardrails and mechanisms to assess agent reliability and safety.
• Build and stress-test agentic AI and RAG systems, evaluating agent behaviour and identifying failure modes.
• Generate synthetic data to support AI testing and evaluation.
• Extend evaluation coverage to new AI risk areas and use cases.
• Collaborate with product teams on evaluation methods and with customer technical teams on requirements and implementation.

Required profile

• 2-3+ years of experience in AI/ML engineering.
• Proven experience in production-grade LLM application engineering.
• Clear spoken and written English (B2+).

Required skills

• Strong hands-on experience building agentic AI systems, including agent harnesses and guardrails.
• Strong Python programming skills.
• Hands-on experience designing, building or testing agentic AI and RAG systems.
• Understanding of AI reliability, safety, testing methodologies and failure-mode handling.
• Experience generating synthetic data for AI evaluation.
• Preferred: AI governance and security frameworks (e.g. AI Verify, NIST AI RMF, OWASP Top 10 for LLMs), AI red-teaming or assurance experience, computer vision, and experience delivering AI solutions to customers.