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 infrastructure team, responsible for designing and building the foundational systems that power automation across Dwelly's operations. The role bridges complex operational workflows with engineering, turning manual processes into reliable AI-driven systems as the company scales through agency acquisitions.
Key responsibilities include:
**Agentic Infrastructure**: Design core primitives for agentic systems including memory, context management, tool-calling, orchestration, and feedback loops. Move from one-off AI solutions toward reusable infrastructure enabling rapid, reliable workflow automation.
**Evaluation & Observability**: Build evaluation frameworks to understand agent performance and failure modes. Establish testing, tracing, debugging, and evaluation as fundamental engineering practices for AI systems.
**Agentic Development**: Push forward how LLMs are used to build software. 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. Make informed decisions about when to use LLMs versus traditional software.
**Operational Automation**: Act as the bridge between operational teams and engineering. Understand real workflows across acquired agencies and identify high-leverage automation opportunities.
**Architectural Influence**: Help define architectural patterns for agentic systems as the company scales. You will have significant influence over technical approach, tooling, and engineering standards.
Required qualifications: Strong software engineering background with experience delivering complex systems from idea to production. Hands-on experience building AI/agentic systems in production. Deep understanding of agents, tool use, structured outputs, context management, orchestration, evaluation, and feedback loops. Advanced practical use of modern LLMs with understanding of building reliable workflows around probabilistic systems. Experience with coding agents and agentic development workflows. Strong architectural judgment and ability to decide when to use LLMs, deterministic software, or human intervention. Experience with TypeScript/Node.js or strong Python background with willingness to apply it in TypeScript-first environment. High autonomy, ownership, and comfort with ambiguity. Strong product judgment connecting technical decisions to business outcomes. Fluent English and startup mentality.
