Build an AI orchestrator including intent and slot extraction, policy engine, planner, composer LLM, output guardrails and PII redaction. Implement RAG for motor policy Q&A, authenticated claim-status lookup, prompt engineering, and API/tool integrations. Project runs approximately June–July 2026 (~2 months) on a 3-month contract option.
Project Responsibilities
• Phase 1 build of the AI orchestrator — intent & slot extraction, policy engine, planner, composer LLM, output guardrails, PII redaction.
• Basic RAG for motor policy Q&A.
• Authenticated claim-status lookup.
• Prompt engineering. Active June–July 2026 (~2 months; duration rounded up to nearest 3-month option).
Requirements
An AI engineer who has shipped LLM-based assistants with RAG and tool-calling into production, strong on prompt engineering and grounding/guardrails
Must-haves
• LLM / GenAI application development
• Retrieval-augmented generation (RAG)
• Prompt engineering
• API / tool integration
• Python (assumed — confirm)
Nice-to-have
• OCI Generative AI
• Arabic NLP
• Insurance / regulated domain
• Guardrails & PII handling
Benefits
What you need to know about the Chennai Tech Scene
To locals, it's no secret that South India is leading the charge in big data infrastructure. While the environmental impact of data centers has long been a concern, emerging hubs like Chennai are favored by companies seeking ready access to renewable energy resources, which provide more sustainable and cost-effective solutions. As a result, Chennai, along with neighboring Bengaluru and Hyderabad, is poised for significant growth, with a projected 65 percent increase in data center capacity over the next decade.
