AI Solution/Principal Engineer

About the role

Own AI evaluation for a sovereign multi-tenant agentic AI platform: evaluation harnesses, golden sets, LLM-as-judge calibration, retrieval and agent evaluation, red-teaming, CI/CD quality gates. Arabic and English.

Requirements

• 5+ years building evaluation/test infrastructure
• 1+ year leadership
• AI evaluation expertise
• LLM-as-judge methodology
• Advanced Python, intermediate TypeScript or Java
• Statistics for non-deterministic systems
• CI/CD framework design

What you'll do

• Set evaluation strategy
• Build evaluation harness platform
• Evaluate retrieval and agents
• Prompt injection red-teaming
• Quality gates in CI/CD

Where this was posted

• LinkedIn

  last seen 1h ago
  View on LinkedIn