Staff ML Platform Engineer - Fintech Engineering (m/f/n)
Hybrid
6+ years
English (C1)
Salary
Not stated
Description
The company is building its own fintech platform from the ground up, a large international effort in which engineers shape the architecture and build core fintech components designed to operate at the company's scale.
The team is lean and AI-native, based in Poland, and works greenfield, where early design decisions stay in place for years.
The role sets the ML architecture and modelling standards that credit decisioning depends on, and other teams copy them.
Your daily tools include the feature store, model registry and serving, MLflow and Databricks, agent orchestration graphs, eval harnesses, and model-monitoring and tracing tools. You work with Credit Risk and with the engineers who integrate models into decisioning services.
Responsibilities
Define the modelling, validation, monitoring, responsible-AI and model-risk practices for credit-scoring and MCA merchant-underwriting models across the platform.
Own the full model lifecycle, from feature selection and training method through validation, champion/challenger testing, deployment, and post-production drift and stability monitoring.
With Data Engineering, define point-in-time-correct, production-grade features and shape the feature-store roadmap around modelling needs.
Set the standards for documentation, model cards and adverse-action reasoning so models hold up under regulatory scrutiny.
Design agentic harnesses and loop and graph agent workflows on the feature store for model iteration (experiment, evaluate, retrain, promote) and for model monitoring and observability.
Design agent loops and graphs covering context, tools, state, evals and guardrails so they are reliable, observable and cost-controlled, then codify them as reference patterns the function reuses.
Set the ML engineering team's technical direction, review its designs and code, and mentor Senior and Mid ML Engineers.
Requirements
You enjoy building ML systems that perform in production and survive audit.
You are hands-on: you design and build, and use AI as a daily tool.
7+ years of machine learning engineering in production systems, including 3+ years in credit-scoring, risk modelling or decisioning ML on Spark/Databricks or an equivalent lakehouse.
7+ years of expert Python and ML frameworks (scikit-learn, XGBoost, PyTorch).
Strong credit-risk and underwriting model design: scorecards, gradient boosting, and survival or behavioural models.
Skilled in validation methods: back-testing, champion/challenger, population stability (PSI) and calibration.
Experienced in point-in-time-correct feature engineering, feature-store consumption and MLOps tooling (MLflow, CI/CD for models).
Fluent in explainability and responsible-AI techniques for regulated decisioning (SHAP, model cards, adverse-action reasoning), with working knowledge of regulatory model-risk frameworks.
3+ years with agentic coding tools and loop and graph engineering, including agentic harnesses, context and tool design, evals, guardrails and iteration. You understand LLM behaviour and its trade-offs in depth.
Staff-level: you set standards through influence rather than authority, and mentor through code and design review.
Fluent English (B2+).
Bonus: FinTech, lending or payments ML.
Bonus: model-risk management or regulatory model validation.