Description review

Senior Full-Stack Developer (AI-Assisted)

Productiv Team · Poland · back to the listing

HR standards

54/100

needs work

Title ↔ description

88/100

strong

Reads as

Full-Stack Engineer

100% confident

How others title the same work

Large employers

  • Software Development Engineer, Influencer Management Adobe
  • Senior Software Engineer (EAA) Coinbase
  • Senior Software Engineer, Full Stack (Coinbase Advisor - Agentic Trading) Coinbase
  • Senior Software Engineer (Typescript), AI Clients: Duo CLI GitLab
  • Grafana Labs | Senior/Staff Software Engineer - AI / Agentic apps | 100% Remote (US + Canada) | Grafana Labs

Startups

  • Founding Software Engineer Aglide
  • Product Engineer (Founding team) Aglide
  • AiMi | Full Stack AI Engineer | Remote(Everywhere) | Full-time AiMi
  • Staff Software Engineer AiPrise
  • ALBERT | REMOTE ALMOST ANYWHERE IN THE WORLD | Hiring principal and distinguished ALBERT

What the listing never says

  • 18 bullet points. Long requirement lists deter qualified candidates, who read them as hard gates. Scope clarity
  • No pay range published. Candidates cannot tell whether applying is worth their time. Pay transparency

The listing, marked up

Nothing in the wording of this listing tripped a check. The scores above still judge how complete and coherent it is.

About the role

We are looking for a Senior Full-Stack Developer to help build and harden a TypeScript, front-to-back product built on Next.js 15, React 19, and an AI pipeline powered by Anthropic Claude.

This is a hands-on, high-ownership role on a small team. The near-term roadmap is concrete and already scoped: you won't be inventing directions from scratch, you'll be shipping well-defined systems and leveling up the codebase as you go.

Key Responsibilities

• Build the final pipeline agent (the certification builder), including schema design, LLM prompt and output design, and a review and approval workflow

• Own multi-tenant readiness: role-based access control, a membership model, email invitations, and self-serve workspace provisioning

• Bring database maturity to the project: adopt a formal migration workflow and separate staging from production data

• Lead production hardening: rate limiting and usage budgets for AI endpoints, a cloud IAM and security review, secrets and environment hygiene, and error observability

• Set up engineering process: a CI pipeline and broader test coverage

• Improve the structure of a fast-grown codebase while continuing to ship features

• Make build-vs-buy calls, write specs, and mentor a junior engineer

Required Qualifications

• Deep TypeScript and modern React/Next.js experience (App Router, Server Components, Server Actions)

• Production SaaS backend experience: multi-tenant data models, role and permission systems, and auth flows (OAuth, JWT sessions)

• Relational database maturity: Postgres with an ORM (Prisma preferred), a sound migration strategy, and safe schema changes on a live database

• Distributed-systems fundamentals in a serverless world: queues, webhooks, idempotency, retries and backoff, timeouts

• LLM product engineering experience: prompt design, structured and validated outputs, awareness of token costs, and graceful degradation when a model or data source fails

• Security instincts: able to run a cloud IAM review (GCP or equivalent), reason about tenant isolation across data, storage, and real-time layers, and know where rate limiting and secrets hygiene belong

• Strong judgment and comfort being the most senior engineer on the project

• Strong async communication: clear technical questions, documented decisions, and self-surfaced blockers

Nice to Have

• Real-time collaboration experience (Yjs, Liveblocks, or ProseMirror/Tiptap internals)

• Google Cloud specifics: Cloud Run, workload identity federation, GCS signed URLs

• Experience taking an early-stage product to its first paying customers

All our positions are Remote and are available as Full Time Employment or B2B Contracts

Originally posted on Himalayas

How this was produced

Highlights are found by rule, not by a model: each one is a phrase matched at a known position, and every note is a template we wrote. The two scores come from a typed-decision model (Jev) that reads the listing against the official role definition and real listings for the same role, and returns probabilities rather than prose — it never writes any of the words on this page, and never chooses what to highlight.

Deterministic penalty applied to the HR score: 8 points (from 62 before penalties). Reviewed 21 Sep 2026.