About the Role

We are seeking a highly skilled Data Analytics & Agentic AI Engineer with 4 to 6 years of professional software engineering experience to lead the design and development of autonomous, multi-agent AI systems and advanced Generative AI workflows. 

In this role, you will focus on applying cutting-edge artificial intelligence to automate complex workflows, analyze enterprise data, and streamline processes within the Risk, Compliance, Internal Audit domains ensuring alignment with Internal audit AI integration targeting operating efficiencies. 

You will bridge the gap between advanced AI engineering and enterprise business logic, building intelligent agents capable of reasoning, planning, and executing tasks such as automated document analysis, compliance checks, anomaly detection, and report generation.

Key Responsibilities

• Architect & Build Agentic AI Systems: Design and implement sophisticated single- and multi-agent systems using frameworks like LangGraph, CrewAI, AutoGen or Google ADK to automate end-to-end business workflows and compliance monitoring.
• Develop Advanced RAG & Reasoning Pipelines: Build and maintain robust Retrieval-Augmented Generation (RAG) pipelines to ground agent decisions in authoritative regulatory guidelines, internal corporate policies, and large document repositories.
• Automate Enterprise Workflows: Create tool-calling agents capable of executing secure actions, such as querying enterprise databases, extracting key information from unstructured documents, and generating structured compliance reports.
• Data Analysis & Anomaly Detection: Develop AI-driven pipelines to analyze large-scale transactional and operational data, identifying outliers, discrepancies, and potential risks.
• Implement AI Governance & Guardrails: Engineer robust safety, compliance, and security guardrails (e.g., using Model Context Protocol (MCP), role-based access controls, and PII masking) to ensure AI agents operate transparently, securely, and with full auditability.
• Technical Leadership & Mentorship: Provide technical guidance to cross-functional teams, define AI architecture patterns, and establish rigorous evaluation methodologies (e.g., RAGAS, TruLens) for LLM outputs.

Key Requirements

• Professional Experience: 56 years of hands-on software engineering experience, with at least 23 years dedicated to building and deploying production-grade GenAI and Agentic AI solutions.
• Domain Familiarity: Strong general understanding of risk management, compliance and Internal Audit workflows. 
• Core Programming & Software Engineering: Exceptional proficiency in Python, clean code practices, object-oriented programming (OOP), design patterns, and enterprise-grade CI/CD pipelines.
• Generative AI & LLM Orchestration:
  • Deep understanding of LLM concepts (prompt engineering, function calling, context window management, and model routing).
  • Hands-on experience with LangChain and advanced agentic frameworks (LangGraph, CrewAI, AutoGen, or Agno).
  • Experience with vector databases (e.g., Pinecone, Milvus, Weaviate, Chroma) and semantic search.
• AI Evaluation & Observability: Experience implementing LLM evaluation frameworks (e.g., RAGAS, PromptBench) and continuous monitoring systems to track agent behavior and prevent hallucinations
• Strong verbal and written communication skills.
• Curiosity, ownership and willingness to work in a collaborative environment.
• Demonstrated ability to collaborate effectively with peers and contribute in a highly technical, fast-paced engineering environment.