Boston Consulting Group (BCG) is seeking a senior manager to lead AI Engineering for our Agent Workforce initiative. This role is pivotal in defining the technical vision for an enterprise AI platform designed to automate common tasks across various business functions within Tech@BCG. You will spearhead the development of a non-human, AI-driven workforce, transforming how Change & Communications, User Research & Design, Enterprise Architecture, and other departments operate.

BCG is a global leader in management consulting, renowned for its pioneering role in business strategy since 1963. We empower clients through total transformation, driving growth, building competitive advantage, and delivering significant bottom-line impact. Our success lies in seamlessly integrating digital and human capabilities, leveraging diverse global teams and cutting-edge solutions across consulting, technology, design, and corporate ventures.

This is an opportunity to shape the future of work at BCG by building and fine-tuning advanced AI models and agent systems. You will implement state-of-the-art techniques such as retrieval-augmented generation (RAG), prompt engineering, and robust evaluation frameworks for model quality and safety. Close collaboration with Product Management and engineering leaders will be key to identifying automation opportunities and translating them into production-grade agents.

As the Technical Lead for Agentic Automation, you will architect and build the AI models and agent systems powering our automated workforce. This includes developing retrieval-augmented generation pipelines, mastering prompt and context engineering, and establishing comprehensive evaluation frameworks for AI model quality and safety. You will partner closely with Product Management and engineering leadership to pinpoint tasks suitable for automation and develop production-grade agents.

Your role will involve translating requirements into robust AI solutions using best practices like the Model Context Protocol (MCP) and event-driven architectures. The goal is to enhance throughput, consistency, and overall quality across business functions. You will also serve as the technical authority for AI architecture, setting engineering standards, guiding implementation decisions, and mentoring engineers.

Drive the evolution of AI capabilities from event-driven systems to increasingly autonomous, multi-agent systems capable of managing end-to-end workflows with minimal human oversight. You will lead architecture reviews, assess emerging AI technologies, and ensure all agentic systems are secure, resilient, observable, and compliant with enterprise architecture, governance, and Responsible AI principles, balancing rapid automation with enterprise-grade reliability and operational excellence.

We require a Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field, along with a minimum of 8 years of software engineering experience, including proven technical leadership in designing and deploying enterprise-scale software platforms. Demonstrated expertise in enterprise AI, Generative AI, and intelligent agent architectures is essential, with a strong background in building secure, scalable, production-ready AI solutions on cloud-native, API-first, event-driven architectures using Azure and AWS.

Hands-on experience with fine-tuning and evaluating large language models (LLMs), designing retrieval-augmented generation (RAG) pipelines, and working with vector databases and embedding models is crucial. Proficiency with OpenAI, Azure OpenAI, Anthropic, and Gemini APIs, the Model Context Protocol (MCP), and agent orchestration frameworks like LangGraph or Semantic Kernel is a must.

Experience integrating AI agents into common engineering tools such as Jira and Confluence, CI/CD pipelines, and ITSM or ticketing systems to automate end-to-end workflows is preferred. The ability to influence technical direction and mentor engineers is highly valued. Relevant AI or cloud certifications are considered a plus.