Join Boston Consulting Group, a pioneer in business strategy, as an AI/ML Engineer Manager. We partner with leaders to drive transformative change, blending digital and human capabilities for competitive advantage and bottom-line impact. Our diverse global teams offer deep expertise and a collaborative approach to help clients thrive.

This role focuses on building and deploying LLM-powered features within a large-scale production application. It's a hands-on, full-stack opportunity encompassing backend services, APIs, and intricate LLM systems. You'll leverage AI coding tools and autonomous agents to enhance development workflows and accelerate delivery. Expect to collaborate with international teams across time zones, taking ownership of features from conception to completion.

Bring senior-level Python and LLM engineering expertise to the team. Execute both planning and hands-on technical work independently. Collaborate effectively with Product Owners and other stakeholders to solve complex problems. Work cross-functionally to deliver impactful solutions across teams. Continuously develop your technical expertise and stay current with new technologies. Bring curiosity and drive to expand your skills and knowledge. Use a data-driven approach to solve technical challenges and make informed decisions. Apply systems-level thinking that integrates data science and engineering principles. Take full ownership of the features and projects you work on, delivering high-quality solutions independently.

Minimum 8 years of experience in API development with Python, including at least 2 years specifically focused on developing and experimenting with LLMs. Essential skills include daily use of AI-assisted and agentic coding tools, strong Python proficiency for building REST APIs (e.g., FastAPI), and a solid grounding in NLP and machine learning for LLM systems. Experience with key LLM model APIs (OpenAI, Anthropic), building, deploying, and securing MCP servers, and understanding multi-agent systems are crucial. Proficiency in designing and implementing RAG systems end-to-end, including vector databases and semantic search, along with experience in distributed search technologies (Elasticsearch, OpenSearch, Solr). Familiarity with prompt writing, server-side events, event-driven architectures, and messaging systems is expected. Candidates should possess strong critical thinking and systems thinking skills, with experience debugging and optimizing complex backend systems, and a solid understanding of backend security best practices.