Introduction
A career at IBM Consulting embraces long-term relationships and close collaboration with clients across the globe.
You’ll work with visionaries across multiple industries to enhance the hybrid and AI journey for some of the most innovative and valuable companies in the world. Your ability to create meaningful change for clients is supported by our strategic partner ecosystem and robust technology platforms, including IBM Software and Red Hat.
Curiosity and a constant quest for knowledge form the foundation of success in IBM Consulting. In this role, you’ll be encouraged to challenge the norm, explore ideas beyond your immediate responsibilities, and develop creative solutions that yield groundbreaking impacts for a diverse range of clients. Our culture of evolution and empathy focuses on long-term career growth and development opportunities in an environment that values your unique skills and experience.
Your Role and Responsibilities
We are seeking a Lead AutoGen Engineer with extensive experience in Autogen who has transitioned beyond building RAG pipelines to designing systems that make agentic AI reliable in regulated, high-stakes environments for both client-facing and internal platforms. This position is ideal for someone who has faced the complexities of regulatory language, has built agentic workflows from the ground up, and approaches LLM outputs with a systems engineer's mindset regarding correctness guarantees. This is a hands-on technical leadership role for someone who designs and constructs production-grade agentic systems — not as a research exercise, but as engineering deliverables that operate reliably in compliance-driven, high-stakes environments. The problems you address will not have ready-made solutions, and you will be expected to make architectural decisions, iterate designs, and communicate those decisions clearly to both technical teams and enterprise stakeholders.
What You Will Do
- Design and deliver RAG systems for complex, document-heavy domains by defining ingestion strategies, retrieval architectures, and generation-side optimizations appropriate for the content type and use case.
- Architect multi-agent orchestration systems that coordinate specialized agents using autogen and other frameworks across parallel and sequential workflows, incorporating structured quality evaluation and targeted correction loops into the pipeline.
- Build LLM routing and evaluation infrastructure — selecting models per task, optimizing generation parameters, and ensuring full auditability of outputs for regulated delivery environments.
- Lead end-to-end technical delivery from problem framing and system design through implementation, quality assurance, and stakeholder communication.
- Work across regulated industries including life sciences, insurance, and financial services, understanding what compliance, traceability, and domain accuracy entail at the implementation level.
- Evaluate and implement fine-tuning approaches where retrieval-based solutions fall short, applying sound judgment to determine appropriateness.
- Mentor engineers and establish technical standards for agentic AI development within the practice.
- Collaborate with client stakeholders to translate complex domain requirements into functional system behaviors.
What We Offer
- Individual career path development.
- Access to a variety of training and certification opportunities.
- A culture of knowledge sharing.
- An environment where your ideas are actively valued and implemented.
- The opportunity to work on projects with one of the largest IT companies in the world.
Required Technical and Professional Expertise
- Proven experience (8 years+) in building and iterating on production-grade agentic systems across the full stack — ingestion, retrieval, orchestration, generation, and quality assurance.
- Deep understanding of statistics, probability, data science, machine learning, and transformer architectures.
- Strong expertise in multi-agent frameworks, designing orchestration patterns, parallel agent architectures, feedback loops, and structured output pipelines.
- Comprehensive knowledge of data ingestion and RAG pipeline designs across various content types, retrieval strategies, and generation optimization techniques.
- Extensive experience delivering agentic systems end-to-end in regulated industries.
- Experience with multiple LLM providers, incorporating routing logic, audit logging, and parameter optimization for enterprise and regulated contexts.
- Advanced skills in prompt and context engineering.
- Integration of agentic solutions with cloud platforms such as Azure OpenAI, IBM Watsonx, and AWS, ensuring governance, safety, and monitoring.
- Proficiency in Python and relevant engineering tools, with experience across AWS and GCP.
- A proven track record of delivering agentic systems with measurable operational impact for enterprise clients in regulated industries.
- Advanced database skills across SQL (MySQL, SQL Server), NoSQL (MongoDB, Neo4j), and VectorDBs (CosmosDB, Azure AI Search, FAISS).
- Ability to lead small technical teams, set direction, and ensure delivery quality across complex engagements.
- Strong communication skills, able to present architectural decisions and system behaviors to non-technical audiences including clinical, regulatory, and business stakeholders.
- Language Requirement: Hindi & English – Professional proficiency required for coordination with other teams engaged in the project.
Preferred Technical and Professional Experience
- Experience with clinical or regulatory document workflows such as pharmaceutical submissions, compliance reporting, or structured document generation at scale.
- Experience working with IBM's agentic asset portfolio.
- Familiarity with Model Context Protocol (MCP) and emerging agentic interoperability standards, agentic skills, and tools.
- Demonstrated breadth of agentic architecture application through multi-agent system design beyond a single domain.
Apply online using the form below. Only applications matching the job profile will be considered.