AI Engineer

SLR is seeking an AI Development Engineer who enjoys building AI systems that operate reliably in the real world. This role sits at the intersection of AI engineering, software development, and infrastructure, focusing on designing and implementing production-grade systems powered by large language models (LLMs). You will work hands-on across the full delivery lifecycle—moving quickly from concept to prototype to production. Working closely with product, engineering, and data teams, you will help deliver intelligent applications built on modern AI infrastructure. We value practical builders over academic theory. Success in this role is defined by your ability to design, implement, deploy, and operate real systems that deliver business value. What You Will BuildYou will design and implement systems across the AI stack, including: LLM-powered applications and intelligent agents Model orchestration and tool-use frameworks Retrieval systems and knowledge layers (RAG) MCP-style integration layers connecting models to tools, APIs, and data sources Scalable infrastructure supporting AI workloads Your work will progress rapidly from prototype to production, with real users and real constraints. Key Responsibilities Build AI Systems Design and implement production-grade systems powered by LLMs and modern AI frameworks Develop applications using technologies such as: OpenAI, Anthropic and other LLM APIs LLM gateway Vector databases Agent orchestration frameworks Implement AI Infrastructure Build and operate the infrastructure required to run reliable AI services, including: API services supporting AI applications Orchestration layers between models and tools Retrieval pipelines and knowledge indexing Observability and monitoring for AI systems Scalable backend services Develop MCP and Tool Integration Layers Design integration layers that enable models to interact with external systems, including: API integrations Tool-use systems for agents Connectors to databases, SaaS tools, or internal platforms Structured prompting and function-calling architectures Ship Production Code Move quickly from concept to working product Write clean, maintainable backend code Build testable services Deploy systems in production environments Iterate based on real user feedback Collaborate Across Teams Work closely with product managers, engineers, and designers to turn ideas into working solutions Required SkillsSoftware Engineering Foundations Strong backend engineering experience Proficiency in Python (preferred) or TypeScript Experience building REST APIs and backend services Solid system design fundamentals Debugging and production troubleshooting skills Understand software development lifecycle LLM Application Development Experience building applications using large language models Prompt engineering and structured prompting Tool use and function calling Retrieval-Augmented Generation (RAG) architectures LLM evaluation and iterative improvement Infrastructure and Deployment Hands-on experience deploying production systems Docker and containerization Cloud platforms (AWS, GCP, or Azure) CI/CD pipelines Scalable service architecture Data and Retrieval Systems Experience building and operating knowledge layers Vector databases (e.g. Pinecone, Weaviate, pgvector) Document ingestion pipelines Embedding workflows Search and retrieval optimization Nice to Have Experience with: MCP architectures or tool-connected AI systems Agent frameworks Knowledge graph systems Streaming or event-driven systems Distributed systems design Evaluation frameworks for AI systems What we look for, we are looking for engineers who: Prefer building working systems over discussing them Move quickly while maintaining quality Enjoy solving messy, real-world problems Take ownership from prototype through to production Stay curious about emerging AI capabilities You do not need to know everything—but you should be comfortable learning quickly and shipping continuously. Experience 2–5 years of experience in software engineering, AI engineering, or ML systems We value evidence of building, including: Shipped products Real systems running in production Open-source contributions Side projects and experimentation Demonstrated delivery matters more than credentials. Why Join SLR You will help build real AI systems at a time when the AI stack is still rapidly evolving. This role offers: Meaningful ownership and autonomy Real engineering challenges The opportunity to shape how intelligent software is designed, built, and deployed across SLR SummaryLocation: London, UKType: Full time

Full job description from WhatJobs. Apply for this role →