AI Software Engineer
This team owns and operates a core service that runs AI-powered agents and their associated infrastructure, ensuring reliability, scalability, and ease of use for internal and external stakeholders. You will work across backend systems, front end integration, and AI/ML workflows, with opportunities to expand your expertise in prompt engineering, Retrieval Augmented Generation (RAG), and large language model (LLM) interactions.
Responsibilities
- Design, build, and maintain services and infrastructure that manage AI powered agents.
- Develop backend services in Python, with comprehensively tested and self documented APIs.
- Work with Agentic AI frameworks and implement prompt engineering best practices to build scalable foundational platform.
- Work with relational databases (MySQL) to store, query, and optimise structured data.
- Collaborate with product and research teams to refine and implement the product roadmap.
- Support front end teams using React/JS components and wrappers for AI driven experiences.
- Learn, apply, and optimise RAG systems, including vector databases, embeddings, and document chunking strategies.
- Build a practical understanding of how large language models (LLMs) work and deepen expertise in effective interactions with LLMs for agent orchestration.
- Monitor, debug, and optimise system performance, ensuring high reliability in production environments.
Skills & Qualifications
- Strong proficiency and experience working with Python based services.
- Hands on experience with relational databases (MySQL or similar).
- Familiarity with React and ability to support front end AI integrations.
- Basic understanding of large language models and eagerness to expand knowledge.
- Demonstrated interest or experience in prompt engineering and working with LLMs.
- Strong problem solving, debugging, and collaboration skills.