Agent / AI Engineer

The role

You will build the AI layer of the GCC Intelligence Platform, the conversational agent users talk to. You will own grounding, retrieval, persona routing, session state and permission-aware querying so the agent stays accurate, secure and tenant-safe.

What you will do

• Integrate LLM APIs (e.g., Azure OpenAI or equivalent) for conversational workflows
• Build a grounding layer that anchors responses to real platform data
• Maintain prompt templates across multiple personas and use-cases
• Implement intent classification and persona routing to the right KPI views
• Build the API handler that sets DB session variables so RLS/ABAC policies enforce correctly
• Own JWT validation and permission registry lookups that control access
• Build session state management, safe retries and failure handling
• Implement token budgeting, tracking and enforcement per tenant
• Improve accuracy baselines through structured evaluation and regression checks

Required qualifications

• 3+ years building with LLM APIs in production (OpenAI, Azure, Anthropic or similar)
• Experience shipping grounding/RAG systems to real users
• Strong Python for agent logic, APIs and prompt management
• Understanding of how auth/session context interacts with database queries
• Prompt engineering across user types and tasks
• Accuracy-first mindset
• Strong debugging and evaluation discipline

Benefits

• Steep learning curves, honest feedback and early ownership
• Chance to see your work influence real business decisions

Before you apply

• Zinnov is an equal opportunity employer

About the company

Zinnov is a global management consulting firm with over 450 professionals across 10 global offices. It helps enterprises, technology companies and investors make data-led decisions about investment, global scaling and growth.