Artificial Intelligence Engineer

About the role

We are seeking an Artificial Intelligence Engineer to design, build, and deploy large‑language‑model (LLM) based agents in production environments. The role focuses on end‑to‑end development, from concept through design, implementation, and operational monitoring.

Key responsibilities

• Develop and ship LLM‑driven autonomous agents using frameworks such as LangChain, LangGraph, CrewAI or equivalents.
• Architect Retrieval‑Augmented Generation (RAG) pipelines, including embeddings, vector stores, chunking and reranking.
• Integrate managed AI services on AWS (Bedrock, AgentCore) and Microsoft (Foundry, Agent Service) into scalable solutions.
• Design robust APIs (REST/GraphQL) and ensure seamless integration with existing systems.
• Implement containerised deployments, Infrastructure as Code, and observability (logging, tracing, metrics).
• Document and showcase work through open‑source contributions, technical blogs or conference talks.

Required profile

• Proven track record of shipping AI agent systems in production or open‑source projects.
• Ability to work autonomously on complex technical problems with minimal supervision.
• Strong problem‑solving mindset and evidence of real‑world AI applications.

Required skills

• Python with strong async programming experience.
• LLM‑based agent development and orchestration frameworks (LangChain, LangGraph, CrewAI, Strands Agents).
• RAG architecture components: embeddings, vector databases, chunking, reranking.
• Managed AI services on AWS (Bedrock, AgentCore) and Microsoft (Foundry, Agent Service).
• API design and integration (REST, GraphQL).
• Containerisation, Infrastructure as Code, and cloud deployment.
• Observability tools for logging, tracing, and metrics.