AI Product Developer
Posted 1 day ago by Haystack
£500 Per day
Outside
Hybrid
Leeds, England, United Kingdom
Summary: The AI Product Developer role involves building production-ready Copilots and LLM applications using Azure AI and advanced architectures. The position requires deep expertise in Generative AI and collaboration with cross-functional teams to develop scalable AI solutions. The role is based in Leeds and offers a competitive day rate. Immediate start is available for qualified candidates.
Key Responsibilities:
- Architect and deploy sophisticated LLM-powered applications and AI agents using Azure OpenAI and LangChain frameworks.
- Engineer high-performance RAG pipelines, optimizing embeddings and vector search capabilities for maximum accuracy.
- Build and integrate custom Copilot solutions and prompt libraries into existing enterprise system architectures via secure APIs.
- Establish robust AI observability and monitoring frameworks to track model performance, reliability, and token consumption.
- Collaborate with cross-functional teams to prototype "Agentic" workflows and develop reusable connectors for various cloud-native data sources.
Key Skills:
- Deep technical expertise in Generative AI, LLMs (GPT-4), and RAG implementation patterns.
- Advanced hands-on experience with the Azure AI ecosystem, including Azure OpenAI Service and AI Search.
- Proficiency in Python and modern agent frameworks such as LangChain, Semantic Kernel, or Copilot Studio.
- Strong background in vector databases (e.g., Pinecone, Weaviate, or Azure AI Search) and embedding strategies.
- Solid understanding of DevOps/MLOps principles, including CI/CD pipelines, containerization, and secure-by-design engineering.
Salary (Rate): £500 daily
City: Leeds
Country: United Kingdom
Working Arrangements: hybrid
IR35 Status: outside IR35
Seniority Level: undetermined
Industry: IT
AI Product Developer | £400 - £500 We're working with a high-velocity enterprise AI innovation foundry on this exciting opportunity. They are at the forefront of engineering intelligent ecosystems that transform how modern enterprises operate through cutting-edge Generative AI. This is a high-octane role for a GenAI specialist to build production-ready Copilots and LLM applications from the ground up. You will leverage Azure AI, RAG architectures, and advanced vector databases to deploy scalable, secure-by-design AI agents that solve complex business challenges at scale.
The Role
- Architect and deploy sophisticated LLM-powered applications and AI agents using Azure OpenAI and LangChain frameworks.
- Engineer high-performance RAG pipelines, optimizing embeddings and vector search capabilities for maximum accuracy.
- Build and integrate custom Copilot solutions and prompt libraries into existing enterprise system architectures via secure APIs.
- Establish robust AI observability and monitoring frameworks to track model performance, reliability, and token consumption.
- Collaborate with cross-functional teams to prototype "Agentic" workflows and develop reusable connectors for various cloud-native data sources.
What You'll Need
- Deep technical expertise in Generative AI, LLMs (GPT-4), and RAG implementation patterns.
- Advanced hands-on experience with the Azure AI ecosystem, including Azure OpenAI Service and AI Search.
- Proficiency in Python and modern agent frameworks such as LangChain, Semantic Kernel, or Copilot Studio.
- Strong background in vector databases (e.g., Pinecone, Weaviate, or Azure AI Search) and embedding strategies.
- Solid understanding of DevOps/MLOps principles, including CI/CD pipelines, containerization, and secure-by-design engineering.
What's On Offer
- Competitive day rate of £400 - £500 per day (Outside IR35 potential depending on status).
- Modern hybrid working model based in the heart of Leeds.
- The chance to work within a specialist AI Foundry on high-impact, enterprise-grade products.
- Immediate start available for a consultant ready to make an instant impact.
- Apply via Haystack today!