Search & AI Retrieval Lead

Every day, somewhere in the world, important decisions are made. Whether it is a private equity company deciding to invest millions into a business or a large corporation implementing a new strategic direction, these decisions impact employees, customers, and other stakeholders. Consulting and private equity firms come to proSapient when they need to discover knowledge to help them make great decisions and succeed in their goals. It is our mission to support them in their discovery of knowledge. We help our clients find industry experts who can provide their knowledge via interview or survey: we curate this knowledge in a market-leading software platform; and we help clients surface knowledge they already have through expansive knowledge management. As our Search & AI Retrieval Lead, you’ll define how structured data, semantic understanding, and intelligent systems come together to power discovery across our platform. From knowledge graphs to LLM-driven enrichment and recommendation systems, you’ll be at the forefront of building something genuinely cutting-edge — with real impact on how our users experience and navigate information. The key duties of this role will include: Search Architecture Strategy: Evaluate and define the future search stack (technology selection is part of the role). Design a scalable, cloud-native search architecture from first principles. Decide between and combine approaches such as: Keyword search Vector search Hybrid retrieval Graph-based retrieval LLM re-ranking Design indexing, data modeling, and ranking strategies. Define measurable relevance and quality frameworks. Knowledge Graph & Intelligent Retrieval: Design and implement a Knowledge Graph architecture modelling entities and relationships. Define graph schema, linking strategies, and enrichment workflows. Combine graph-based signals with semantic search and ranking models. Build extraction pipelines on top of frontier models (OpenAI, Gemini). Develop modern recommendation systems leveraging structured + unstructured data. Data & Cloud Infrastructure (GCP-first): Architect retrieval pipelines on Google Cloud Platform (GCP). Design data pipelines and feature stores using BigQuery or alternative analytical systems. Ensure scalability, observability, and cost efficiency. Build production-grade systems, not experiments. 5+ years building and scaling production search or retrieval systems. Strong experience designing search architectures, not just operating them. Experience evaluating and selecting search technologies. Experience with semantic search and embeddings-based retrieval. Experience building pipelines on top of frontier LLMs (OpenAI, Gemini). Strong Python skills. Experience leading technical initiatives in mid-sized teams. Experience working with cloud-native systems (preferably GCP). Tenure Gifts - Vouchers, extra holiday and sabbaticals for each year of employment. Health insurance through Vitality Employee Assistance Programme - Access to a health and wellbeing service that offers personalised advice and support from specialist teams. Enhanced Maternity & Paternity pay. Annual Leave - 25 days + bank holidays which includes a week's closure over the Christmas period to fully reset. MyMindPal app - Online support for mental fitness that helps people to stress less and enjoy life more Corporate Events - From quarterly gatherings to our annual winter & Summer parties, we love to celebrate, collaborate and have fun together! We are committed to building an inclusive workplace – did you know that marginalized groups are less likely to apply to jobs unless they meet every requirement listed? If you are interested in the above role, but don’t necessarily tick every box, we encourage you to apply anyway – this role could still be a great match! Take a look at our diversity statement here.