Location: London or Cardiff, UK (Hybrid/Flexible)Salary: £80,000 – £90,000 DOE (Plus equity options)

About Us

We are a proptech company at the forefront of AI and data innovation, partnering with leading insurance firms and major banks to deliver intelligent, scalable solutions for the property sector. Our work blends deep technical expertise with the reliability, security, and compliance required by highly regulated industries.

We design and build systems that collect, integrate, and process hundreds of data sources — from live APIs and large-scale web crawls to internal datasets — and connect them to cutting-edge AI models, including fine-tuned LLMs and retrieval-augmented generation (RAG) pipelines. Our solutions enable smarter property decisions, faster operations, and better customer outcomes for both the financial services and property sectors.

Key Responsibilities

Data Acquisition & Integration

• Design, implement, and operate pipelines ingesting and normalising data from APIs, databases, web crawlers, and file imports.
• Architect secure, scalable web crawling and data ingestion systems suitable for regulated environments.

AI Development & RAG Implementation

• Prepare, clean, and structure datasets for fine-tuning LLMs and retrieval-based workflows.
• Design, implement, and optimise RAG pipelines using vector databases, embeddings, and semantic search to connect real-time and historical data to LLMs.
• Deploy, evaluate, and refine AI agents using GPU-enabled cloud infrastructure.
• Build and maintain prompt engineering and evaluation frameworks for enterprise-grade AI applications.
• Lead the end-to-end architecture for AI data ingestion, processing, and retrieval workflows with a focus on security, compliance, and scalability.
• Mentor engineers and data scientists, promoting best practices for AI in regulated industries.

Insights & Automation

• Automate extraction of technical and business insights from large datasets for property and financial services use cases.
• Optimise performance and cost-efficiency of compute and retrieval operations.

Required Skills & Experience

• Proven experience designing and maintaining complex data pipelines from multiple sources.
• Strong expertise in large-scale web crawling & scraping.
• Proficiency in Python and one or more of: Node.js, Go, Java.
• Deep experience in RAG — from embeddings and vector database design to semantic search optimisation and retrieval integration with LLMs.
• Experience with LLM fine-tuning and evaluation.
• Hands-on experience with GPU cloud platforms for model training and inference.
• Understanding of data security, privacy, and compliance in regulated industries.
• Database knowledge across SQL, NoSQL, and document stores.
• Familiarity with ETL/ELT frameworks and distributed data processing.
• Ability to lead complex technical projects and mentor other engineers.

Nice-to-Have Skills

• Experience with LangChain, LlamaIndex, or other RAG orchestration frameworks.
• Familiarity with model evaluation tools.
• Background in proptech, insurance, or financial services data ecosystems.
• Exposure to MLOps pipelines for continuous AI delivery in enterprise environments.

What We Offer

• Flexible, hybrid working arrangements.
• Opportunity to deliver high-impact AI solutions for the property and financial services sectors.
• Culture of innovation combined with enterprise-grade quality and governance.

Apply to careers@planna.co with your CV and a short description of your most impactful RAG or AI pipeline project.