AI Engineer – Agentic Systems & Automation – £70,000 – Fully remote in UK
A fast-growing company at the forefront of engineering innovation and AI automation is seeking an experienced AI Engineer to help develop intelligent, scalable agentic systems integrated into modern software development lifecycles.
This role involves leading the design and deployment of LLM-powered agents, developer tools, and automation frameworks that streamline workflows and elevate productivity.
This is a hands-on engineering role that blends software development, AI experimentation, and product innovation.
The successful candidate will play a key role in architecting agent-based systems, leveraging advanced frameworks such as LangChain and LlamaIndex, and deploying real-time AI capabilities that integrate deeply with SDLC processes.
Key Responsibilities
* LLM Agent Development: Design and implement intelligent, multi-step agents using frameworks like LangChain, LangGraph, and LlamaIndex to enhance developer workflows.
* Tooling & Assistant Innovation: Develop AI-powered assistants and developer tools with an emphasis on scalability, performance, and reliability.
* AI Engineering: Build, test, and optimize generative AI features using platforms such as OpenAI, Claude, and Gemini, including fine-tuned custom models and evaluation pipelines.
* Prompt Engineering: Design, iterate, and test prompt strategies to improve model accuracy, robustness, and responsiveness across various LLM backends.
* Cross-Functional Collaboration: Work closely with engineering, product, and QA teams to embed agent-led automation within CI/CD pipelines and developer environments.
* Prototyping & R&D: Drive rapid prototyping efforts and validate new ideas through real-world experimentation and user feedback.
* Responsible AI: Promote ethical and secure AI practices, proactively addressing issues like prompt injection, data leakage, and model drift.
* AI Advocacy: Lead internal workshops, demos, and documentation initiatives to promote AI capabilities across teams and client projects.
Ideal Candidate Profile
* Agentic Experience: Proven experience building agent workflows using frameworks such as LangChain, LangGraph, or equivalent.
* AI/ML Expertise: Solid understanding of large language models (LLMs), embeddings, vector search, and prompt engineering.
* Software Engineering Skills: Strong programming skills in Python (AI pipelines) and TypeScript (full-stack integration). Capable of writing production-grade code.
* Product Mindset: Ability to understand user needs and translate them into impactful AI features and experiences.
* Cloud & Data Knowledge: Experience working with cloud platforms (AWS, Azure, or GCP).
* Model Deployment: Familiarity with evaluating, fine-tuning, and deploying LLMs in production environments, including performance monitoring and optimization.
* Collaboration & Agility: Comfortable working in fast-paced, cross-functional teams.
* Experimental Approach: A passion for rapid iteration, learning from experiments, and data-driven development.
Preferred Qualifications
* Experience designing RAG (Retrieval-Augmented Generation) or CAG systems using vector databases and hybrid retrieval techniques.
* Knowledge of LLM security challenges, including prompt injection and adversarial attacks.
* Familiarity with prompt evaluation frameworks and metrics such as truthfulness, helpfulness, and toxicity.
* Hands-on experience with developer-focused AI tools (e.g., Copilot, Cursor), including a deep understanding of their architecture and scalability.