WHAT YOU'LL DO
To realize our aspirations to build a Gen AI assistant that will transform the way BCG works, we are looking for LLM engineers who are passionate about designing, developing, and optimizing GenAI products. You will work within the LLM Squad and your Squad Leader in your domain of expertise, helping to advance the work and using your experience to maximize Squad performance. You will bring expertise in full stack development, Performance, and stability of custom-built products. This role is involved in all aspects of LLM based application including LLM expertise, Data science/ML, backend development including API and core functional logic. Work would also involve documentation of all designs and development.

Among your responsibilities, you will:Continuously developing your expertise:Keeping your technical skills and knowledge sharp, ensuring you remain up-to-date with the latest industry trends and innovations, both internally and externally.Staying well-versed in the tools, methods, and technologies that best serve your team’s needs.Sharing knowledge and expertise: Actively contributing to knowledge-sharing within your team and across related teams, ensuring alignment with technical roadmaps and guidelines. Bringing insights from your domain expertise to discussions, helping to guide technical direction and best practices.Contributing to the Squad’s success: Working with your Squad to achieve its mission by advancing tasks based on the priorities set by the Product Owner. Collaborating cross-functionally, leveraging your expertise to support the Squad’s goals and deliver impactful results.Identifying and supporting resource needs: Identifying where technical expertise is needed and suggesting ways to fill any gaps, whether through your own contributions, training, or advocating for new resources.Adapting to the organization’s new ways of working:Actively embracing and supporting the organization’s new working models, including Agile practices.Contributing to a positive and collaborative team culture by embodying the values of the new way of working
YOU'RE GOOD AT
Being a highly skilled Senior AI and LLM Engineer.Executing both planning and hands-on technical work independently.Collaborating effectively with Product Owners and other stakeholders to solve complex problems.Working cross-functionally to contribute to impactful solutions across teams.Continuously developing your technical expertise and staying up-to-date with new technologies.Being passionate, intellectually curious, and driven to expand your skills and knowledge.Using a data-driven approach to solve technical challenges and make informed decisions.Applying your systems-level thinking, integrating both data science and engineering principles.Taking full ownership of the features and projects you work on, delivering high-quality solutions on your own.
YOU BRING (EXPERIENCE & QUALIFICATIONS)
BA degree in Computer Science, Statistics, or related field with a focus on Artificial Intelligence, Machine Learning, or Natural Language Processing[2+ years of experience developing and experimenting with LLMs3+years of experience developing AI/ML technologies within large and business critical applicationsExperience & Skills (Mandatory)Proficiency in Python and all associated DS libraries and frameworksStrong knowledge in AI, machine learning, and natural language processingExperience with leveraging, training and fine-tuning Foundation Models, including multimodal inputs and outputsStrong experience working with key LLM models APIs (e.g. OpenAI, Anthropic) and LLM Frameworks (e.g. LangChain, LlamaIndex)Experience with multi-agent frameworks/systems and an understanding of multi-agent systems and their applications in complex problem-solving scenarios.Experience with unstructured.io or similar libraries for handling various document formats and extracting structured information from unstructured data.Expertise in using LlamaIndex for building and querying knowledge bases, including its data connectors, indexing strategies, and query engines.Knowledge of effective text chunking techniques for optimal processing and indexing of large documents or datasets.Proficiency in generating and working with text embeddings using models like BERT, GPT, or domain-specific embedding models. Understanding of embedding spaces and their applications in semantic search and information retrieval.Experience in constructing and querying knowledge graphs, including technologies like Neo4j or RDF triplestores. Understanding of ontology design and graph-based reasoning.Experience with RAG concepts and fundamentals (vectorDBs, semantic search, etc.), Expertise in implementing RAG systems that combine knowledge bases with generative AI models.Experience & Skills (Nice to have)Experience with cloud infrastructure for AI/MLExperience with LLM guardrailsExperience with LLM monitoring and observabilityExperience with security related to LLM integration
YOU'LL WORK WITH

Your AI Engineering chapter, by setting their direction, establishing objectives and key results, working on the staffing and development of your chapter, and ensuring that you maximize outputs and working products.

Tribe Leaders, Product Owners and other Tribe Chapter Leads with whom you shall work to manager chapter resources and ensure a positive collaboration.

Agile Coaches and Scrum Masters, that will ensure that you adopt agile principles, mindset and ways of working into your daily routine and who will coach you during the transformation.

Squad members of a specific squad, led by a Product Owner.