Description

You will lead the design and implementation of enterprise-grade agentic AI systems, focusing on multi-agent orchestration and RAG pipelines. You will own the end-to-end lifecycle of AI-driven workflows, ensuring deterministic hand-offs, feedback loops, and strict adherence to data governance and responsible AI practices.

Responsibilities

• Design and implement multi-agent systems (Document, Requirement, Scenario, Test Case, Automation Agents) with deterministic hand-offs and feedback loops.
• Architect and optimize Retrieval-Augmented Generation (RAG) pipelines, including hierarchical chunking, embedding strategies, vector DB selection, and context window optimization.
• Develop and manage agentic frameworks (LangChain, LangGraph, Semantic Kernel, AutoGen) for large-scale agent concurrency and parallel document processing.
• Integrate LLMs into enterprise SDLC workflows, implementing prompt layer refinement, few-shot prompting, structured output generation, and guardrails to prevent hallucinations.
• Establish data governance, AI ethics, and compliance standards for all AI-driven solutions and LLM platforms.

Required Skills

• 10+ years of experience in software engineering, machine learning, data science, or artificial intelligence.
• 3+ years of hands-on expertise with LLM frameworks, evaluation tools, or observability platforms (Langfuse, LangChain, Azure AI).
• Strong proficiency in Python, PowerShell, Splunk, ServiceNow, Jira, Confluence, and SharePoint.
• Deep understanding of multi-agent orchestration, lifecycle management, and incremental regeneration strategies.
• Experience with Vector databases, Embedding models, Retrieval strategies, and enterprise LLM platforms (Azure OpenAI, OpenAI).
• Proven track record of implementing end-to-end AI-driven workflows and fine-tuning models.
• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.

Key Skills

Education

Bachelor's or Master's degrees