The posting
Kindgeek is looking for an AI Engineer who treats model output as a hypothesis, not an answer.
We’re looking for someone who can build multi-agent systems and still clearly understand where a probabilistic call must stop and a deterministic rule must take over.
Your mission will be to design and run the AI layer of a production fintech platform for our US-based client, where agents extract and reconcile data from real, messy documents — and every number they touch is eventually checked against a rule that never guesses.
You’ll work in a small, senior team with direct ownership from architecture to production behavior.
Responsibilities
As an AI Engineer (TypeScript), you will be responsible for:
- Designing multi-agent extraction and orchestration pipelines where each agent retrieves and uses only the context relevant to its task, rather than relying on naive keyword or similarity search.
- Building structured extraction, classification, and drafting features with output validation and clear boundaries against deterministic business logic.
- Integrating in-house ML prediction and detection endpoints into product features, handling timeouts and low confidence without fabricating a value.
- Making AI and ML behavior measurable through tracing, evaluation, and prompt/agent iteration, so quality is observed, not assumed.
- Designing durable, event-driven workflows around LLM and ML calls that handle retries, partial failures, and idempotency.
- Working with real, messy documents as first-class input — parsing, chunking, and structuring mixed financial and unstructured content.
- Writing production TypeScript across the backend, with typed contracts between AI services and the rest of the system.
Requirements
We’re looking for an AI Engineer (TypeScript) who has:
- Production experience designing or operating multi-agent AI systems, including how agents store, catalog, and hand off extracted context to each other.
- Practical experience shipping at least one LLM-powered feature to production, and the ability to describe a specific failure mode you found and how you contained it.
- Hands-on daily use of AI coding tools such as Claude Code, Codex, or equivalent, with clear judgment about what to verify before trusting their output.
- Strong production TypeScript and Node.js experience, comfortable with ESM and typed API contracts such as tRPC, GraphQL, or equivalent.
- Experience consuming ML predictions in application code, understanding confidence and uncertainty well enough to decide what the product should do when a model is wrong or unavailable.
- Experience with asynchronous, event-driven backend work — job queues or durable workflow engines — and the operational instincts that come from running them.
- Working knowledge of PostgreSQL or another relational database in production, including schema and migration basics.
- The ability to walk through a real technical trade-off you made and explain the reasoning behind it, rather than just describing the theory.
- Strong spoken English and direct, low-ego communication, comfortable working closely with a US client in a small team.
Will be a plus
- Document ingestion and extraction experience across mixed-format files — OCR, PDFs, structured and unstructured data.
- Modern React/Next.js experience, for engineers who also touch the product surface.
- Prior experience in fintech, regtech, or another regulated, high-trust domain.
WHAT WILL YOU GET WITH KINDGEEK We want you to thrive and feel supported
- Professional growth: at Kindgeek, we want our employees to grow and achieve ambitious professional goals. We support professional development with training and certification refunds and provide regular feedback and technical reviews.
- Benefits package: Kindgeek offers all team members competitive compensation and a benefits package that includes 18 working days of fully paid vacation, 10 compensated by 50% sick leaves without a note from the doctor, and an opportunity to take study leaves. Depending on how long you stay in the company, you can receive different health insurance packages from our partners.
- Personal growth: as a part of our team, you will have access to corporate English courses with a 50% reimbursement, take advantage of our offline library and access a large selection of corporate training and classes. Also, every employee can request any internal or external training or certification if it applies to his or her work responsibilities.
- Geek community: at Kindgeek, we value community — even in the full-scale invasion times, we take every opportunity to stick together. Our geeks organise various online and offline clubs — from stretching and skiing to English. We volunteer together and support each other.
- Flexibility: Kindgeek offers a hybrid working model. Team members can work remotely or from the office or Kindgeek London Hub — an innovative cafe-style co-working in Lviv (it’s pet-friendly!).
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.
