Location: Newcastle upon Tyne or Remote (UK)- PERM
We’re working with a growing technology organisation looking to expand its engineering capability with a number of AI Developers. You’ll play a key role in building intelligent, scalable features, leveraging the latest in LLMs, retrieval-augmented generation (RAG), and cloud-native technologies.
There are multiple roles available, ranging from mid-level to senior engineers, offering opportunities to both deepen technical expertise and take ownership of AI initiatives.
What You’ll Be Doing
* Design and build AI-powered features using modern LLM frameworks
* Develop and optimise RAG pipelines (vector databases, embeddings, retrieval strategies)
* Integrate AI services into existing backend systems and APIs
* Work with structured and unstructured data to improve model outputs
* Collaborate with cross-functional teams to deliver high-impact features
* Contribute to architecture decisions and help shape AI capability
* Ensure performance, scalability, and reliability of AI systems in production
* RAG: Vector databases (e.g. Pinecone, Weaviate, or similar)
* Cloud: Azure, AWS, or GCP
* Frontend collaboration: any modern JS framework (desirable)
What We’re Looking For
Mid-Level
* 2–4+ years of software development experience
* Exposure to AI/ML or LLM-based applications
* Understanding of APIs, backend systems, and cloud environments
* Interest or hands-on experience with RAG or semantic search
Senior-Level
* 5+ years of experience in software engineering
* Strong experience designing and deploying AI-driven systems
* Proven experience building or scaling RAG architectures
* Ability to lead projects, mentor others, and influence technical direction
#J-18808-Ljbffr