AI Engineer

AI Engineer (Contract, 2 Months - Possible extensions)

Location: UK Remote

Our client is an exciting, ambitious, rapidly growing AI powered Property Tech business. Due to rapid start-up growth, they now require a passionate AI Engineer to join the team on a contract basis for 2 month initial period. The successful candidate will help build and scale advanced AI-driven applications, with a strong focus on production-ready LLM workflows, efficient architecture, and seamless integrations.

You’ll work alongside a tight-knit team of engineers and product leads who are deeply committed to building responsible, high-impact AI systems. If you’re excited by the intersection of AI, software engineering, and emerging agentic architectures—this is your place.

The business is an ambitious, fast-moving team building next generation AI-native systems — products that think, learn, and adapt in real time. The vision is to redefine how intelligent software interacts with the world, enabling capabilities that feel more like working with a creative partner than a machine. We’re looking for someone who’s not just skilled but obsessed with AI. If you're driven by curiosity, excited by experimentation, and motivated to contribute to a team building meaningful and novel AI experiences, we want to hear from you.

Minimum Requirements:

• Strong Python skills with clean, maintainable code.
• Proven production experience with LLM workflows and scaling them in real-world applications.
• Solid understanding of advanced prompt engineering techniques.
• Good knowledge and practical experience with FastAPI and RESTful APIs.
• Solid knowledge of PostgreSQL.
• Experience with DevOps/MLOps, including deploying and monitoring ML pipelines.
• Good understanding of audio protocols (e.g., WebRTC, SIP, RTP).

Preferred (Bonus) Skills:

• Production experience with Agno or Phidata.
• Familiarity with Microsoft Autogen or CrewAI agent frameworks.
• Experience with LlamaIndex (formerly GPT Index).
• Practical experience with memory frameworks like Mem0 or Letta.
• Understanding and production experience with traditional RAG and agentic RAG architectures.
• Strong grasp of embedding systems and vector databases (e.g., Pinecone, Weaviate, FAISS).
• Production experience with LiveKit or similar audio/video platforms.

What You’ll Be Doing:

• Building and deploying scalable AI features, agents, and services powered by LLMs.
• Prototyping and refining advanced prompt strategies and memory techniques.
• Contributing to backend and front-end components for real-time, interactive applications.
• Collaborating closely with product and infrastructure teams to ship impactful features.
• Driving clean and reliable deployments with MLOps best practices.