We automate end to end candidate compliance for education recruitment agencies using deterministic, AI powered workflows. We collect and validate documents, execute compliance rules, and produce a fully auditable clearance outcome for every candidate. We are early, moving fast, and building something technically interesting. Agentic compliance pipelines, rules engines, and document processing AI on top of a clean FastAPI and Next.js stack.
The Role
You will own both sides of the stack. Backend heavy in practice, focused on compliance logic, agentic workflows, and third party integrations, but you will also ship the React and Next.js surfaces that compliance teams and candidates use every day. This is not a lite frontend, serious backend split. We care deeply about both. The admin dashboard and candidate portal need to be fast, clear, and polished.
What You Will Do
Backend
Build and maintain FastAPI services that power compliance checks, document validation, and third party integrations
Design and implement durable, auditable workflow logic with a strong focus on traceability
Integrate external APIs including DBS providers, professional registers, and identity verification services
Write high coverage tests first. TDD is not optional here, it is how we work
Own database schema design and query performance on Postgres
Frontend
Build the candidate portal and admin dashboard in Next.js with a component first approach
Implement clean, accessible user interfaces using shadcn ui and Tailwind, with opinionated defaults rather than custom CSS
Keep frontend data fetching patterns tight using React Query, typed API contracts, and clear state management
Ship features end to end. You spec, build, test, and deploy
AI Engineering
Build compliance agents that validate candidate data, cross reference records, and review documentation against regulatory requirements
Implement browser automation for access to external verification portals, including selector resilience, failure recovery, and evidence capture
Instrument LLM workflows with observability tooling including traces, evaluations, prompt regression tests, and scoring pipelines
Maintain prompt quality through structured evaluation workflows. Broken prompts should fail CI
How We Work
Tests are written before or alongside implementation
Backend stack includes FastAPI, Postgres using Neon, and Temporal Cloud for durable workflows
Frontend stack includes Next.js, shadcn ui, and Tailwind
Pull requests are small, reviewed quickly, and merged to main frequently
We are not looking for someone who ticks every box. If you are strong on backend, care about code quality, and can build a solid frontend, we would like to talk.
Requirements
What We Are Looking For
Must have
Strong Python and FastAPI experience with a solid understanding of async and clean service design
Solid React and Next.js skills. You can build a good looking, functional UI without hand holding
Practises TDD. Red, green, refactor is your default loop
Comfortable with relational databases including schema design, migrations, and query optimisation
Experience with REST APIs and third party integrations
Browser automation using Playwright or similar tools, including scripting, evidence capture, and reliable selectors
Strong Git hygiene including meaningful commits, small pull requests, and constructive code reviews
Nice to have
Experience with workflow orchestration such as Temporal
Familiarity with regulated environments or compliance adjacent products
Experience with shadcn ui, Radix, or similar headless component libraries
Exposure to LLM powered document processing or agentic systems and frameworks such as LangChain or Mastra
Experience with LLM evaluation workflows including prompt regression testing, scoring pipelines, and observability tools such as Langfuse, Braintrust, or LangSmith
Agentic engineering experience including declarative specs, skills, subagents, AGENTS.md, and ADRs
Experience building B2B SaaS products including multi tenancy, tenant isolation, external APIs, webhooks, and data feeds