Full-Stack Engineer

pYou own features end to end: the data model, the services, the agent tooling and the screens. On a given week you might wire a new weather dataset into the signal library, give Kite a new tool for structuring a drought cover, harden the rolling-window trigger logic that decides whether a policy pays out, and build the review screen an underwriter uses to approve it. /p pThe core of the platform is agentic. Kite plans, calls tools, runs analysis on client data and produces regulated outputs. Making that reliable — evaluations, guardrails, observability, graceful failure, a human approval step that never gets skipped — is as much the job as any CRUD endpoint. /p pYou will work directly with the CTO and have a large say in architecture, stack and how we build. The platform is growing fast and the next 12 months will set its shape for years. /p h3What you'll do /h3 ul liDesign, build and run backend services for WeatherWise Studio and WeatherWise Construction: APIs, data pipelines, pricing and simulation engines, integrations. /li liBuild and extend the agent layer — tools, orchestration, memory, evaluation harnesses and the observability needed to trust an agent in a regulated workflow. /li liOwn the weather data engine: ingestion from 180k+ stations and gridded datasets (ERA5 and others), storage, indexing and fast querying of decades of history. /li liShip the front end of your own features in React/TypeScript to a high standard, working with our design-led front-end engineer on the system. /li liBuild the embedded API strategy: clean, well-documented, versioned APIs that let brokers and carriers run WeatherWise inside their own systems. /li liOwn reliability and security: CI/CD, infrastructure as code, monitoring, incident response, and the controls a regulated firm needs. /li liUse AI tooling as a first-class part of how you work, and help the whole team get more from it. /li /ul h3What we're looking for /h3 h3You must have /h3 ul li6+ years building and running production systems, with real ownership of backend, infrastructure and front end. /li liStrong Python and TypeScript. We care about fluency across the stack more than any single framework, but you should be able to ship a clean React screen as readily as a well-designed service. /li liHands-on experience building LLM-powered or agentic systems in production: tool use, orchestration, prompt and context design, evaluation, and the failure modes that come with them. /li liSolid data engineering: pipelines, time-series and geospatial data at scale, and the judgement to pick the right store and query pattern. /li liCloud and DevOps competence (AWS or GCP, containers, infrastructure as code, CI/CD, observability). /li liDaily, serious use of AI coding tools (Claude Code, Cursor or similar) and a view on how to work well with them. /li liComfort in a small, senior team: you scope ambiguous problems yourself, make pragmatic calls and ship. /li /ul h3It would be great if you also have /h3 ul liExperience with weather, climate or geospatial data (NetCDF/Zarr, ERA5, gridded reanalysis, station networks). /li liWorked on pricing, simulation or risk models, or in insurance, fintech or another regulated domain. /li liDesigned public APIs used by third parties. /li liBuilt evaluation frameworks for LLM applications. /li /ul pbWe care far more about what you have shipped than which exact tools you used. /b /p h3Company Benefits /h3 ul liFully remote /li li4 day work week /li liPlenty of learning and career progression /li /ul