AI Engineering Lead

Department: Enterprise AI & Innovation
Reports To: Head of AI Strategy & Enablement

Required Qualifications:

• 7+ years in AI/ML engineering, with 3+ years in GenAI or LLM-based systems.

• Proficiency in Python and hands-on experience with LangChain, LangGraph, and OpenAI APIs.

• Deep understanding of RAG, multi-agent orchestration, and prompt engineering.

• Experience deploying AI solutions on Azure, AWS, and Google Cloud Platform.

• Familiarity with enterprise AI governance, risk frameworks, and security standards.

Key Responsibilities:

• Architecture & Engineering

• Design and implement RAG architecture patterns, multi-agent systems, and LLM interfacing pipelines

• Lead hands-on development using LangChain, LangGraph, and other orchestration frameworks for LLMs

• Build scalable AI workflows across cloud platforms (Azure OpenAI, AWS Bedrock, Google Cloud Platform Vertex AI)

• Prompt Engineering & Optimization

• Apply structured prompt frameworks (e.g., RISEN) for task-specific tuning and ethical content generation

• Develop reusable prompt libraries and templates for enterprise use cases.

• Agentic AI System Design

• Architect and deploy multi-agent systems for enterprise workflows, including decision trees, dynamic orchestration, and fallback logic

• Evaluate agentic capabilities for productivity, automation, and user interaction.

• Technology Evaluation & Best Practices

• Compare and benchmark GenAI frameworks (LangChain vs LangGraph) for performance, flexibility, and maintainability

• Define and document best practices for secure, scalable, and ethical AI deployment

• Governance & Compliance

• Ensure adherence to AI risk management policies (AEMP80, AENB80) and GenAI certification standards

• Collaborate with InfoSec, Legal, and Cloud Governance teams to align architecture with enterprise controls.