Deloitte

AI Engineer - RAG (Retrieval-Augmented Generation) / Vector Databases and Langchain

⭐ - Featured Role | Apply direct with Data Freelance Hub
This role is for an AI Engineer - RAG, focusing on Retrieval-Augmented Generation, Vector Databases, and LangChain in London. Contract duration is 6 months, with a pay rate classified as inside IR35. Key skills include Python, Prompt Engineering, and cloud infrastructure experience.
🌎 - Country
United States
πŸ’± - Currency
$ USD
-
πŸ’° - Day rate
Unknown
-
πŸ—“οΈ - Date
April 28, 2026
πŸ•’ - Duration
More than 6 months
-
🏝️ - Location
Hybrid
-
πŸ“„ - Contract
Inside IR35
-
πŸ”’ - Security
Unknown
-
πŸ“ - Location detailed
City Of London, England, United Kingdom
-
🧠 - Skills detailed
#Cloud #Databases #AI (Artificial Intelligence) #Classification #Deployment #Langchain #Azure #Python #Documentation #Microsoft Azure #Scala
Role description
Contract Role: AI Engineer - RAG (Retrieval-Augmented Generation) / Vector Databases and Langchain Contract Location: London. 2/3 days hybrid Contract Duration: 6 months Contract Start Date: Immediate Contract Classification: Inside IR35 Role Overview We are supporting a leading financial services organisation in hiring an experienced AI Engineer to support the development and optimisation of advanced GenAI solutions. This role will focus heavily on Retrieval-Augmented Generation (RAG), Vector Databases, Prompt Engineering, and LangChain frameworks to enhance enterprise AI capabilities. The successful candidate will play a key role in designing, building, and improving scalable AI applications, working closely with technical and business stakeholders to deliver high-impact solutions within a fast-paced environment. Key Responsibilities β€’ Design, build, and optimise AI solutions using Retrieval-Augmented Generation (RAG) frameworks β€’ Develop and maintain integrations with Vector Databases for efficient retrieval and contextual generation β€’ Work extensively with LangChain to build and enhance LLM-based applications β€’ Apply strong Prompt Engineering techniques to improve model performance and output quality β€’ Develop scalable Python-based solutions to support GenAI initiatives β€’ Collaborate with engineering, architecture, and business teams to translate requirements into technical delivery β€’ Support continuous improvement of AI workflows, performance, and governance standards β€’ Contribute to documentation, testing, and deployment best practices Required Skills & Experience β€’ Strong Python development experience β€’ Proven experience with Prompt Engineering and LLM optimisation β€’ Hands-on experience with Retrieval-Augmented Generation (RAG) β€’ Strong understanding of Vector Databases and retrieval frameworks β€’ Experience using LangChain in enterprise or production environments β€’ Experience working within cloud-based infrastructure and modern engineering environments β€’ Strong problem-solving and stakeholder management skills Preferred Skills β€’ Experience with Microsoft Azure β€’ Experience with Agent Development Kit (ADK) β€’ Exposure to enterprise AI governance and production deployment of GenAI solutions β€’ Financial services experience preferred but not essential