Generative AI Engineer

Job Title: LLM Developer

Location: West London, UK (Hybrid Working)

Type: Contract (Inside IR35)

Duration: 12 Months

Brief:

We are seeking a highly skilled LLM Developer to design, build, and deploy a web-based AI agent that will automate and elevate our core QA coordination tasks.

Responsibilities:

• Design & Implement NLP Pipelines: Parse, understand, and extract key information from unstructured Release Notes and Test Policy documents.
• Develop RAG Systems: Fine-tune a Retrieval-Augmented Generation (RAG) system, training models on QA policies for accuracy and context-awareness.
• Build AI Agent Architecture: Utilize modern LLM APIs (e.g., OpenAI, Anthropic, Gemini) and frameworks (e.g., LangChain, LlamaIndex) to create a robust system.
• Integrate Backend APIs: Enable the AI agent to automatically publish generated test guides to our internal web platform.
• Create Web-Based UI: Develop a simple, effective interface for QA teams to interact with, review, and override AI outputs if necessary.

Requirements:

• Bachelor's degree in Computer Science, AI, or a related technical field.
• Experience in software development (Backend or Full-Stack).
• Strong proficiency in Python or other backend languages (e.g., Node.js, Java) and frameworks (e.g., Flask, Django, Express).
• Proven experience building applications using LLM APIs (e.g., OpenAI) in commercial or production-level environments.
• Hands-on experience with AI frameworks like LangChain or LlamaIndex.
• Experience designing or building agentic AI systems

If this sounds of interest, please apply here or reach out to daniel@microtech-global.com