About the role
This is a hands-on founding engineering role where you will have significant ownership over architecture, technical direction, experimentation, and productionization.
Responsibilities:
- Design and build production-grade LLM and Agentic AI systems from 01.
- Develop multi-step AI agents capable of tool calling, reasoning, planning, and autonomous task execution.
- Build agent orchestration using LangGraph, LangChain, or equivalent frameworks.
- Implement agent memory, state management, context management, and retrieval systems.
- Build RAG pipelines using embeddings, vector databases, retrieval, ranking, and context optimisation.
- Design and maintain LLM evaluation and testing frameworks/harnesses for measuring agent and model performance.
- Work with multiple LLM providers/models such as OpenAI, Anthropic, Gemini, open-source models, etc.
- Build AI feedback loops using production trajectories, evaluations, user feedback, and task outcomes.
- Optimise latency, token usage, inference cost, reliability, and task success rate.
- Develop APIs and backend services using Python / FastAPI / Go / Node.js or equivalent.
- Build production infrastructure using Docker, Kubernetes, cloud platforms, CI/CD, observability, and monitoring.
- Collaborate closely with founders and product teams to identify high-impact AI use cases and rapidly prototype solutions.
- Establish engineering best practices for AI reliability, evaluation, observability, safety, and scalability.