Overview
In this role you design and build production-grade AI systems powered by large language models. You will work across AI engineering, software, and infrastructure to deploy reliable, real-world applications. You collaborate with product, engineering, and data teams to move ideas from concept to production, delivering tangible business value. You’ll shape scalable AI infrastructure and integration layers, tackling real-user constraints. This is a hands-on, fast-moving opportunity to influence how intelligent software is designed and deployed at SLR.
Responsibilities
- Design and implement production-grade AI systems powered by LLMs and modern AI frameworks
- Develop applications using OpenAI, Anthropic and other LLM APIs; implement LLM gateway, vector databases, and agent orchestration
- Build and operate AI infrastructure: API services, orchestration layers, retrieval pipelines, monitoring, and scalable backend services
- Develop MCP and Tool Integration Layers: API integrations, tool-use systems, connectors to databases/ SaaS tools, structured prompting and function-calling architectures
- Ship production code: rapid prototyping to production, maintainable backend services, testable deployments, iteration from user feedback
- Collaborate with product managers, engineers, and designers to turn ideas into working solutions
Key requirements
- 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
- Experience building applications with large language models
- Prompt engineering and structured prompting
- Tool use and function calling
- Retrieval-Augmented Generation architectures
- LLM evaluation and iterative improvement
- Hands-on experience deploying production systems
- Docker and containerization
- Cloud platforms (AWS, GCP, or Azure)
- CI/CD pipelines
- Scalable service architecture
- Vector databases (e.g. Pinecone, Weaviate, pgvector)
- Document ingestion pipelines
- Embedding workflows
- Search and retrieval optimization
- Practical, hands-on mindset
- Ownership and accountability
- Ability to iterate quickly while maintaining quality
- Python
- TypeScript
- REST APIs
AI Engineer in London employer: RCS Global Group
SLR is an exceptional employer, offering a dynamic and collaborative work culture that prioritises professional development and employee well-being. With a comprehensive benefits package, including competitive salaries, excellent healthcare, and flexible working arrangements, employees are empowered to thrive both personally and professionally. As a Data Engineering Lead, you will play a pivotal role in shaping the future of data engineering within a globally recognised consultancy, with ample opportunities for career progression and impactful contributions to sustainability solutions.
