Introduction
A career in IBM Consulting offers an exciting opportunity to build long-term relationships and collaborate closely with clients worldwide. You will partner with visionaries across diverse industries, enhancing their hybrid and AI journeys as they strive for innovative and valuable solutions. Your ability to create meaningful change for clients will be bolstered by our extensive strategic partner ecosystem and robust technology platforms, which include IBM Software and Red Hat.
At IBM Consulting, curiosity and a relentless pursuit of knowledge form the bedrock of success. You will be encouraged to push boundaries, explore ideas beyond your immediate role, and devise creative solutions that yield groundbreaking impacts for a broad network of clients. Our culture emphasizes growth and empathy, ensuring a nurturing environment that values your unique skills and experience while promoting long-term career development.
In this position, you will be based in one of our IBM Consulting Client Innovation Centers (Delivery Centers), where we provide in-depth technical and industry expertise to a diverse array of public and private sector clients. Our delivery centers empower clients with locally-based skills and technological expertise, fostering innovation and accelerating the adoption of new technologies.
Your Role and Responsibilities
We are seeking a Lead AutoGen Engineer with extensive experience in Autogen who has progressed beyond simply building RAG pipelines. You will design systems that ensure agentic AI remains reliable in regulated, high-stakes environments for both client-facing and internal platforms. This position is perfect for someone who has grappled with the challenges of working with complex regulatory language, built agentic workflows from the ground up, and approaches LLM outputs with the analytical mindset of a systems engineer focused on correctness guarantees.
This hands-on technical leadership role requires you to design and build production-grade agentic systems as deliverables that comply with stringent requirements. The problems you will tackle are complex and do not have off-the-shelf solutions. You will be expected to make architectural decisions, iterate on initial designs when necessary, and effectively communicate your decisions to both technical teams and enterprise stakeholders.
What You Will Do
- Design and deliver RAG systems for complex, document-heavy domains, including defining ingestion strategies, retrieval architectures, and generation-side optimizations appropriate to specific content types and use cases.
- Architect multi-agent orchestration systems that coordinate specialized agents using autogen and other frameworks across parallel and sequential workflows, incorporating structured quality evaluations 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, encompassing problem framing, system design, implementation, quality assurance, and stakeholder communication.
- Work across regulated industries, including life sciences, insurance, and financial services, gaining an understanding of compliance, traceability, and domain accuracy at the implementation level.
- Evaluate and apply fine-tuning approaches when retrieval-based solutions fall short, using discernment to choose the most appropriate method.
- Mentor engineers and establish technical standards for agentic AI development within our practice.
- Collaborate with client stakeholders to translate intricate domain requirements into functioning system behaviors.
What We Offer
- Individual career path development.
- Access to countless training and certification opportunities.
- A culture of knowledge sharing.
- An environment where your ideas are actively encouraged and valued.
- The possibility of working on projects at 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.
- Extensive knowledge of statistics, probability, data science, machine learning, and transformer architectures.
- Strong expertise in multi-agent frameworks, including designing orchestration patterns, parallel agent architectures, feedback loops, and structured output pipelines.
- Deep understanding of data ingestion and RAG pipeline designs across diverse content types, retrieval strategies, and generation optimization techniques.
- Comprehensive experience delivering agentic systems end-to-end to production pipelines within regulated industries.
- Experience integrating multiple LLM providers with routing logic, audit logging, and parameter optimization for enterprise and regulatory contexts.
- Advanced skills in prompt and context engineering.
- Capability to integrate 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; experience with cloud platforms like AWS and GCP.
- A track record of delivering agentic systems with measurable operational impact for enterprise clients in regulated industries.
- Advanced database skills in SQL (MySQL, SQL Server), NoSQL (MongoDB, Neo4j), and VectorDBs (CosmosDB, Azure AI Search, FAISS).
- Ability to lead small technical teams, set direction, and maintain delivery quality across complex engagements.
- Strong communication skills to effectively present architectural decisions and system behaviors to non-technical audiences, including clinical, regulatory, and business stakeholders.
- Professional proficiency in Hindi and English, essential for coordinating with other teams involved in the engagement.
Preferred Technical and Professional Experience
- Experience with clinical or regulatory document workflows, including pharmaceutical submissions, compliance reporting, or structured document generation at scale.
- Previous work with IBM's agentic asset portfolio.
- Familiarity with Model Context Protocol (MCP) and emerging agentic interoperability standards, encompassing agentic skills and tools.
- Demonstrated breadth of multi-agent system design applications beyond a single domain.
Apply online using the form below. Only applications matching the job profile will be considered.