Kindgeek is looking for an AI engineer who wants to commit to one product for the long run — someone who cares about the outcome, adapts quickly as the product evolves, and stays with a hard problem until users actually feel it is solved.
Your mission will be to help a U.S. company in the tax incentives domain turn manual, expert-heavy workflows into reliable production software, where AI and ML extract, predict and suggest, and deterministic logic owns every final figure.
The product is live and in real use: the MVP is already working for users, and the team is actively building new capabilities on top of it. You will join a small core engineering team, work directly with the CTO, and see the impact of your decisions immediately.
RESPONSIBILITIES
As an AI Engineer (Typescript), you will be responsible for:
- Building multi-agent document pipelines that extract data from dozens of real client files — financial tables, long narratives, scans and diagrams — and hand it off reliably to downstream agents;
- Designing the boundary between probabilistic AI/ML output and the deterministic engine that owns every calculated figure, with validation, provenance and human review where needed;
- Integrating in-house ML predictions (scoring, estimation, anomaly detection) and defining what the product does when a model is uncertain, wrong or unavailable;
- Making AI behaviour measurable through tracing, evaluation and meaningful tests, so quality is observed rather than assumed;
- Building durable, event-driven workflows and integrations that handle retries, idempotency, partial failure and unreliable third-party services;
- Owning AI features end-to-end — from an ambiguous business problem through the data model, typed APIs and UI to stable production behaviour;
- Working closely with the CTO and product — making trade-offs and risks explicit, sharing context and documenting key decisions.
REQUIREMENTS
We're looking for an AI Engineer (Typescript) who has:
- Hands-on production experience with multi-agent or tool-calling architectures — for example, agents that extract data from documents and hand it off to other agents through explicit data contracts;
- At least one shipped LLM-powered feature — with a concrete story of how it failed on real data and how you contained it, without letting the system invent a value;
- 5+ years of commercial software engineering experience with real end-to-end ownership of production features;
- Strong TypeScript / Node.js in production — senior engineers with a Python background are welcome if ready to work in a TypeScript codebase from day one;
- Working experience with modern React / Next.js, including complex forms, server state and caching;
- PostgreSQL in production: schema design, migrations on live data, history and auditability;
- Hands-on experience with queues, workflow engines or event-driven systems (e.g. Inngest, Temporal, BullMQ, SQS, Kafka);
- Engineering discipline: tests that catch real regressions, observability, CI/CD, and careful verification of AI-generated code;
- Product mindset — you can explain what a product does and for whom, and you think in outcomes rather than tickets;
- Fluent spoken English and readiness to work roughly 11:00–20:00 Kyiv time.
Will be a plus:
- Experience with document processing (OCR, structured extraction) for large, messy real-world files;
- Background in fintech, regtech or another regulated, high-trust domain;
- Familiarity with parts of the current stack: tRPC / Zod, Prisma, AWS, Sentry / OpenTelemetry / Langfuse, Vitest / Playwright.
WHAT THIS ENGAGEMENT OFFERS
A product you can grow with: Long-term product, not a rotation: you work deeply on one product with a dedicated team — no staff augmentation, no short-term projects;
Real ownership: a small core team (around five engineers plus an ML specialist and QA), direct work with the CTO and room to make technical decisions;
Top-of-market compensation: a fixed rate plus KPI-based performance compensation;
Fully remote: work from anywhere, with core collaboration hours of roughly 11:00–20:00 Kyiv time;
AI-native engineering: AI is part of both the product and the way the team builds it, so you will work with current tools and approaches every day.
We encourage you to apply
At Kindgeek, we encourage everyone to apply – regardless of nationality, race, gender, marital status, disability, sexual identity, or religion. We are growing into an inclusive, equal-opportunity company where only professionalism, competence, and ideas matter. We are committed to supporting mobilised employees and veterans joining Kindgeek and facilitating their career development. We aim to bring equal opportunities to all team members and candidates – especially those underrepresented in technological companies.