BCG U - Senior AI Engineer

Role Overview
BCG U is building a new generation of AI-based solutions for professional skilling, performance development and capability building — combining BCG U's proprietary knowledge with large language model technology to deliver personalised coaching and skill development at scale.
This is a strategically important and growing area for BCG U. The successful candidate will work across the full lifecycle of these initiatives — from refining and validating the technical architecture through to overseeing and contributing to delivery. The role requires someone who is equally comfortable thinking through design decisions and getting into the detail of the build. The role is structured as a 12-month contract with meaningful work from day one. Scope may span one or more initiatives depending on business need.

What You’ll Do
Work with BCG U's product and knowledge leadership to refine and validate the technical architecture for AI skilling solutions — challenging assumptions, identifying gaps and ensuring the design is sound before build begins
Make and document key technical decisions covering cloud infrastructure, LLM integration patterns, API design, data architecture, vector store configuration and security
Produce technical specifications that external vendor teams can build from, and provide hands-on oversight of their delivery against those specifications
Establish coding standards, review processes and architectural guardrails that maintain quality and protect BCG U's IP throughout the build
Design and implement LLM integration patterns including RAG pipelines, model-agnostic abstraction layers and prompt engineering frameworks
Ensure security, data governance and privacy requirements are correctly implemented — encryption, tenant isolation, RBAC and GDPR compliance
Identify and manage technical risks across the delivery lifecycle
Contribute to BCG U's broader thinking on how AI-based solutions in this space should be architected as the technology and the business evolve

You Bring (Experience & Qualifications)
Experience
7–10 years in software engineering with at least 3 years hands-on experience building and delivering LLM-based products in production
Direct experience with RAG architectures, prompt engineering, vector databases and LLM evaluation frameworks — this is the core of the role
Comfortable making and owning architecture decisions on cloud infrastructure, API design and data architecture
Experience producing technical specifications and overseeing external development vendors against them
Background in enterprise software delivery — security, data governance and scalability are familiar territory

Technical skills
LLM APIs: Anthropic Claude, OpenAI GPT-4, Google Gemini or equivalent — hands-on, not advisory
Vector stores: Azure AI Search, Pinecone, Weaviate or equivalent
Cloud platforms: Azure (preferred), AWS or GCP
Speech and multimodal: Azure Cognitive Services, ElevenLabs, HeyGen or equivalent
Security: encryption standards, GDPR, tenant isolation, SSO and RBAC implementation
API design, microservices and containerisation

Attributes
Spans design and delivery comfortably — as rigorous about architecture decisions as about the quality of what gets built
Clear communicator who can explain technical decisions to non-technical stakeholders
Genuinely excited about AI and its application to learning, skilling and professional development
Comfortable with ambiguity and able to move at pace without perfect information
Fluency with claude chat and claude code and other gen ai tools a strong plus