Overview :
We are looking for an AI Product Engineer to join our team full-time on-site. This role is for someone with good LLM understanding, strong Python development skills, and hands-on experience in prompt and context engineering for building agents. You will own the technical roadmap of our AI Agents, ensuring smooth delivery from concept to deployment, and translating research breakthroughs into usable product features.
Key Responsibilities :
- Design, refine, and optimise prompts for LLMs (OpenAI, Anthropic, Google, etc.) to achieve high-quality, reliable outputs.
- Develop and maintain Python scripts and lightweight services that integrate LLM APIs and manage context, prompts, and agent logic.
- Build LLM-powered workflows and mini-agents , using function calling, structured outputs, and reasoning strategies.
- Collaborate with engineering / product teams to translate requirements into prompt-driven AI behaviours .
- Conduct systematic testing, evaluation, and iteration of prompts, models, and workflows.
- Maintain prompt libraries, evaluation frameworks, and test harnesses in Python.
- Support integration of LLM workflows into larger systems (not heavy backend development).
- Debug prompt behaviours, API flows, and logic issues alongside engineering teams.
Minimum Requirements :
Strong Python skills (must-have), including : writing clean scripting-level code, calling APIs, handling JSON, data flows, and simple automationsPractical experience working with LLMs , including prompt design, context handling, and reasoning patterns (CoT, ReAct, ToT, etc.).Experience using LLM APIs and SDKs (OpenAI, Anthropic, Google, etc.).Understanding of LLM agent concepts : tool calling, function calling, routing, and structured reasoning.Ability to test, debug, and improve prompt behaviours via Python.Strong analytical thinking and attention to detail.Ability to independently experiment, iterate, and prototype.