Senior AI Engineer - Agentic Systems

IBM
Chicago, IL, United States
6 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
7 years minimum
Working hours
Regular working hours
Job source

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Microsoft Azure Continuous Integration Memory Management Azure Machine Learning Search Technologies Enterprise Application Integration Data Logging Enterprise Software Applications Large Language Models Multi-Agent Systems
+7 more
Prompt Engineering Generative AI Operational Systems Data Management Machine Learning Operations Virtual Agents Microservices

Job description

We are seeking a skilled AI Engineer to join an active enterprise AI engagement in a hands-on, client-facing capacity. This is a senior individual contributor role requiring deep technical proficiency in Agentic AI - you will be expected to operate independently, interact directly with the client, and deliver with minimal oversight.

You will be responsible for building, fine-tuning, and operationalizing AI solutions on Azure, with a specific focus on agentic workflows, prompt engineering, RAG pipelines, and production-grade model deployment. The client expects a high-caliber engineer who can perform from day one.

What You’ll Do

Agentic AI Development

  • Design, build, and deploy agentic AI workflows and multi-agent systems using Azure OpenAI and supporting frameworks

  • Develop and optimize prompt engineering strategies to maximize model performance and reliability

  • Build and maintain Retrieval-Augmented Generation (RAG) pipelines that enable grounded, context-aware AI responses

  • Implement agent orchestration patterns including tool calling, memory management, and human-in-the-loop workflows

Client Engagement & Collaboration

  • Engage directly with client stakeholders to gather requirements, demo capabilities, and walk through technical solutions

  • Communicate clearly on progress, blockers, and technical tradeoffs - no hand-holding required

  • Collaborate with architects, data engineers, and business teams to ensure seamless end-to-end integration

Engineering & Operationalization

  • Deploy and manage AI models using Azure ML, Azure AI Studio, or equivalent Azure services

  • Integrate AI capabilities into enterprise applications via APIs, event-driven pipelines, and microservices

  • Establish monitoring, evaluation, and feedback loops to ensure ongoing model performance and reliability in production

  • Ensure solutions meet enterprise standards for security, scalability, and compliance

Required technical and professional expertise

  • 7+ years designing, developing, and deploying scalable AI applications leveraging LLMs, RAG architectures, and agentic AI workflows.
  • Build and operationalize AI orchestration pipelines using frameworks such as LangChain and LangGraph.
  • Develop AI agents capable of tool calling, contextual retrieval, memory/state management, multi-agent coordination, and autonomous workflow execution.
  • Implement MCP (Model Context Protocol) integration patterns to enable secure, modular interoperability between AI agents, enterprise systems, tools, and data sources.
  • Support the industrialization of AI capabilities through reusable architecture patterns, standardized deployment frameworks, monitoring, testing, evaluation pipelines, and operational support models.
  • Develop and integrate enterprise-grade APIs, vector databases, workflow platforms, and operational systems into AI-enabled business processes.
  • Implement AI governance, security, logging, guardrails, and human-in-the-loop controls to support responsible and scalable AI adoption.
  • Contribute to CI/CD, LLMOps/MLOps, and cloud-native deployment practices supporting enterprise-scale AI delivery.

Requirements

Preferred technical and professional experience

Preferred Skills

  • Experience with agentic frameworks such as LangChain, LangGraph, AutoGen, Semantic Kernel, or CrewAI

  • Familiarity with vector databases (e.g., Azure AI Search, Pinecone, Weaviate) for RAG implementations

  • Knowledge of MLOps practices and CI/CD pipelines for AI model deployment and lifecycle management

  • Experience with enterprise integration patterns and connecting AI solutions to CRMs, ERPs, or data platforms

About the company

A career in IBM Consulting is built on long-term client relationships and close collaboration worldwide. You’ll work with leading companies across industries, helping them shape their hybrid cloud and AI journeys. With support from our strategic partners, robust IBM technology, and Red Hat, you’ll have the tools to drive meaningful change and accelerate client impact. At IBM Consulting, curiosity fuels success. You’ll be encouraged to challenge the norm, explore new ideas, and create innovative solutions that deliver real results. Our culture of growth and empathy focuses on your long-term career development while valuing your unique skills and experiences.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on dejobs.org

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:08 min

Essential engineering roles in the generative AI space

Mary Grygleski Mary Grygleski · LIVE

1:10 min

Exposing sensitive information through partial search logs

Dennis Schulz Dennis Schulz +1 · WWC Europe 2026

3:07 min

Transitioning architecture to microservices at Netflix

Steve Upton Steve Upton · WWC 2022

2:37 min

Tracing the evolution from early AI to generative AI

Mike Mike · WWC 2025

3:30 min

Current AI tools adopted across engineering teams

Himanshu Vasishth Himanshu Vasishth +3 · WWC 2025

1:56 min

Discovering incidents using logs, metrics, and traces

Nele Uhlemann · WWC 2023

Videos

See all

Related articles

See all