AI Engineer

Design and Develop AI Services: Build AI-powered solutions to enhance employee experience and address HR technology use cases.

• Integrate and Optimize LLMs: Work with large language models (LLMs) and intelligent systems, primarily using Azure OpenAI and other cloud-native AI tools.
• Apply Advanced AI Patterns: Utilize architecture patterns like Retrieval-Augmented Generation (RAG), Agentic RAG, MCP, Function Calling, and A2A for enterprise applications.
• Engineer Prompt and Context Pipelines: Develop robust pipelines for prompt design, context handling, embeddings, chunking, and real-time data integration.
• Evaluate and Optimize Models: Test and enhance model output and application performance for relevance, robustness, fairness, and explainability.
• Implement Responsible AI Controls: Apply guardrails, prompt testing, adversarial/bias testing, and controls for responsible AI application delivery.
• Deploy Cloud-Based Solutions: Build and scale AI applications on Azure Cloud Services, including Azure OpenAI and Azure AI Search.
• Ensure Quality and Security: Deliver secure, reliable, observable, maintainable, and well-documented AI solutions.

Strong Python programming abilities.

• Experience developing and optimizing cloud-based AI applications.
• Familiarity with AI/ML and agentic frameworks (e.g., LangChain, LangGraph, Pydantic).
• Advanced knowledge of AI architecture patterns, especially in Azure environments.
• Understanding of GPT token usage, latency, analytics, and budget controls.
• Experience with prompt engineering, vector databases, embedding/chunking, and real-time data integration.
• Hands-on experience with Azure OpenAI and Azure AI Search.
• Commitment to quality, maintainability, documentation, and continuous learning.
• Preferred/Nice to Have:
• Knowledge of alignment and feedback techniques, synthetic data, and human-in-the-loop processes.
• Experience designing evaluation frameworks for explainability, safety, and operational quality.
• Familiarity with packaging AI features for production (logging, monitoring, observability, controlled rollout)., Pragmatic, hands-on engineer capable of building production-grade AI services and integrating LLMs in enterprise environments.