AI Engineer

Mission of the Role

Key Responsibilities

• Build, deploy, and optimize LLM-powered applications, agentic workflows, and RAG-based solutions for enterprise use cases.
• Design and implement scalable AI services leveraging Azure OpenAI, Claude, and other foundation model APIs.
• Develop robust prompt engineering strategies, structured outputs, function/tool calling, and agent orchestration patterns.
• Create end-to-end RAG pipelines, including document ingestion, chunking, embeddings, vector search, re-ranking, evaluation, and monitoring.
• Ensure production reliability through observability, performance optimization, token management, retries, streaming responses, and fault-tolerant architectures.
• Implement Responsible AI practices, including PII protection, prompt injection mitigation, output validation, cost controls, and latency guardrails.
• Develop and integrate AI services using Azure Functions, Service Bus, Key Vault, Document Intelligence, and REST APIs.
• Collaborate with cross-functional teams to convert AI POCs into scalable production-grade solutions.
• Drive continuous experimentation, model evaluation, and innovation in Generative AI and Agentic AI technologies.

Qualifications, Experience and Technical Skills

• .NET / C# integration experience and interoperability with backend systems.
• Experience with MongoDB, Redis, and event-driven architectures.
• Knowledge of model fine-tuning techniques, including LoRA.
• Expertise in embedding model evaluation, selection, and optimization.
• Hands-on experience with multimodal AI solutions involving vision and speech models.
• Familiarity with evaluation frameworks such as Ragas, Promptfoo, and Azure AI Evaluation SDK.
• Experience with containerization and cloud-native deployments using Docker, AKS, and Azure Container Apps.
• Exposure to Human-in-the-Loop (HITL) workflows and AI-assisted user interfaces.