AI Engineer

Design and optimize a multi-phase RAG pipeline combining vector search, LLM orchestration, and safety guardrails. Integrate Azure OpenAI models, manage OpenSearch indices, and develop a safety guardrails framework. Optimize prompts and latency to achieve sub-300ms response times.

• Design and optimize a multi-phase query processing pipeline with deterministic fast-paths, vector search, and parallel processing
• Integrate and manage Azure OpenAI models for query classification, HyDE rewriting, and safety evaluation
• Manage OpenSearch indices for FAQ, SmPC, and PromoMats content with cosine similarity scoring
• Develop and maintain a safety guardrails framework covering adverse events, off-label use, PII detection, and prompt injection
• Optimize LLM prompts, temperature settings, and latency to meet P95 response time targets
• Implement fallback strategies and circuit-breaker patterns for service resilience
• Design global resource pooling (boto3 sessions, thread pools, clients) to minimize per-request overhead

• Hands-on experience with Azure OpenAI and LLM orchestration
• Strong Python skills including async and threaded processing
• Practical knowledge of vector search and OpenSearch
• Experience with prompt engineering, evaluation metrics, and performance tuning

• Safety guardrails design
• Embedding model A/B testing
• Circuit-breaker patterns
• FastAPI