SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Dwelly is building an AI operating system for residential lettings, operating over 15,000 properties and $470M in GMV as one of the UK's ten largest lettings operators. The company has raised $263M and is backed by top-tier investors.
You will be an early core member of the AI engineering team, responsible for designing and building the agentic infrastructure that powers automation across Dwelly's rapidly expanding network of acquired agencies. This is a production-focused role, not research—you'll build systems that must operate reliably at scale.
Key responsibilities include:
**Agentic Infrastructure**: Design core primitives including memory, context management, tool-calling, orchestration, and feedback loops. Move from one-off AI solutions toward reusable infrastructure enabling quick, reliable workflow automation.
**Evaluation & Observability**: Build frameworks to understand agent performance and failure modes. Make testing, tracing, debugging, and evaluating AI systems as fundamental as unit testing in traditional software.
**Agentic Development**: Push how LLMs are used to build software itself. Create workflows where coding agents and specialized subagents can explore repositories, implement changes, review architecture, and iterate with minimal human coordination.
**Orchestration**: Design systems where specialized agents, tools, deterministic software, and humans work together effectively. Develop judgment about when to use LLMs vs. traditional software vs. coordinated multi-agent approaches.
**Operational Automation**: Bridge complex operational workflows and engineering. Work with operational and product teams to identify high-leverage automation opportunities and turn them into production systems.
**Architectural Influence**: Help define architectural patterns for agentic systems as the company scales. You'll have significant influence over technical approach, tooling, and engineering standards.
Required qualifications: Strong software engineering background with experience delivering complex systems end-to-end. Hands-on production experience building AI/agentic systems. Deep understanding of agents, tool use, structured outputs, context management, orchestration, evaluation, and feedback loops. Advanced practical use of modern LLMs (not casual ChatGPT usage). Experience with coding agents and agentic development workflows. Strong architectural judgment. TypeScript/Node.js experience or strong Python background with willingness to apply it in TypeScript. High autonomy, ownership, and comfort with ambiguity. Strong product judgment and communication skills.
