The role is located in Cambridge or Edinburgh. We are building software tools and agentic applications that leverage our AI hardware and large language models. We need software engineers who can design scalable backend systems and integrate advanced LLM capabilities.
Qualifications
* Ability to collaborate effectively within a team and work on-site
* Strong problem-solving skills and attention to detail
* Bachelor’s or Master’s degree in Computer Science or related field
* Experience in LLM-related software development is a plus
Key responsibilities
* Design, build and deploy distributed systems and AI agents that leverage LLMs and retrieval‑augmented generation (RAG) to provide contextual, reasoning‑based capabilities.
* Develop cloud‑native microservices and data pipelines to deliver high‑performance inference and contextual retrieval across multiple data sources.
* Implement frameworks for orchestration, task planning and memory management in agentic architectures, ensuring reliability and operational excellence.
* Collaborate with product managers, researchers and hardware teams to translate novel LLM capabilities into robust applications; stay current with emerging AI and distributed computing technologies.
* Apply best practices for software engineering, including code reviews, automated testing, security and CI/CD; troubleshoot and resolve production issues.
* 5+ years of software development experience building scalable backend systems; strong knowledge of distributed system architecture, concurrency and microservices.
* Experience developing LLM‑powered applications, including prompt engineering, RAG and agentic frameworks.
* Proficiency in one or more programming languages such as Python, Java, Go or Rust; experience with cloud platforms (AWS, Azure, GCP) and container orchestration (Kubernetes).
* Familiarity with AI/ML inference frameworks, vector databases and data streaming systems.
* Strong problem‑solving skills, ability to mentor peers and thrive in a dynamic startup environment.