Negotiable
Undetermined
Remote
England, United Kingdom
Summary: The AI Engineer - Search and Retrieval role involves designing and implementing scalable, cloud-native search architectures for a fast-growing business that aids consulting and private equity firms in accessing high-quality insights. The position requires expertise in various search technologies and the ability to build and scale production-grade search systems. The engineer will also work with modern LLMs and analytical platforms to enhance data retrieval and performance. This is a contract position based remotely in the UK.
Key Responsibilities:
- Define and design a scalable, cloud-native search architecture from the ground up
- Evaluate and select the right technologies across keyword, vector, hybrid, and graph-based search
- Design indexing, ranking, and data modelling strategies
- Establish clear frameworks for measuring search relevance and performance
- Design and implement a knowledge graph to model entities and relationships
- Define schema, linking strategies, and enrichment workflows
- Combine graph-based signals with semantic search and ranking models
- Build extraction and enrichment pipelines using modern LLMs
- Architect scalable retrieval and data pipelines in a GCP environment
- Work with analytical platforms such as BigQuery (or similar)
Key Skills:
- Strong experience building and scaling production-grade search or retrieval systems
- Proven ability to design search architectures from scratch
- Experience working with semantic search, embeddings, and vector-based retrieval
- Hands-on experience building pipelines using LLMs (OpenAI, Gemini)
- Strong Python skills
- Experience working in cloud-native environments (ideally GCP)
- Background leading or owning technical initiatives within a team
Salary (Rate): undetermined
City: undetermined
Country: United Kingdom
Working Arrangements: remote
IR35 Status: undetermined
Seniority Level: undetermined
Industry: IT
AI Engineer Search and Retrieval – Contract – Remote in the UK I’m working with an interesting, fast-growing business that sits at the intersection of data, knowledge, and decision making. They support consulting and private equity firms by helping them access and surface high-quality insight both from external experts and their own internal knowledge.
What you’ll be doing
- Define and design a scalable, cloud-native search architecture from the ground up
- Evaluate and select the right technologies across keyword, vector, hybrid, and graph-based search
- Design indexing, ranking, and data modelling strategies
- Establish clear frameworks for measuring search relevance and performance
- Design and implement a knowledge graph to model entities and relationships
- Define schema, linking strategies, and enrichment workflows
- Combine graph-based signals with semantic search and ranking models
- Build extraction and enrichment pipelines using modern LLMs
- Architect scalable retrieval and data pipelines in a GCP environment
- Work with analytical platforms such as BigQuery (or similar)
What they’re looking for
- Strong experience building and scaling production-grade search or retrieval systems
- Proven ability to design search architectures from scratch
- Experience working with semantic search, embeddings, and vector-based retrieval
- Hands-on experience building pipelines using LLMs (OpenAI, Gemini)
- Strong Python skills
- Experience working in cloud-native environments (ideally GCP)
- Background leading or owning technical initiatives within a team