Staff ML Platform Engineer (Fintech)

Location: Hybrid, ideally one day a week in the Warsaw or Kraków office, Poland

Company

InPost Pay is building a large-scale fintech platform from the ground up, with a lean engineering organization in Poland and AI-native engineering at its core.

What you will do

• Set modelling, validation, monitoring, and responsible-AI standards for credit-scoring and merchant-underwriting models.
• Own the end-to-end model lifecycle, including feature selection, training, validation, champion/challenger testing, deployment, and post-production monitoring.
• Partner with Data Engineering on point-in-time-correct production features and shape the feature-store roadmap.
• Establish model documentation, model cards, adverse-action reasoning, and regulatory model-risk practices.
• Design agentic harnesses and loop or graph workflows for model iteration, evaluation, retraining, promotion, monitoring, and observability.
• Set technical direction, review designs and code, and mentor Senior and Mid ML Engineers.

Requirements

• 7+ years of experience in machine learning engineering for production systems and 3+ years in credit scoring, risk modelling, or decisioning ML on Spark, Databricks, or an equivalent lakehouse.
• Expertise in Python and ML frameworks including scikit-learn, XGBoost, and PyTorch.
• Strong knowledge of credit-risk and underwriting models, model validation, back-testing, champion/challenger testing, PSI, and calibration.
• Experience with point-in-time-correct feature engineering, feature stores, MLflow, model CI/CD, explainability, model cards, SHAP, and responsible AI.
• 3+ years of experience with agentic coding tools, agentic harnesses, context and tool design, evaluations, guardrails, and loop or graph engineering.
• Fluent English at B2+ level.

Nice to have

• Fintech, lending, payments, fraud-detection, or real-time low-latency model-serving experience.
• Model-risk management, regulatory validation, audit, or regulator-facing documentation experience.
• MLOps or feature-store platform ownership.
• Causal inference or uplift modelling for credit-policy experimentation.

Culture & Benefits

• Architectural authority from day one on a greenfield, high-stakes platform.
• Modern ML, feature-store, model-serving, Databricks, MLflow, and agent-orchestration tooling.
• Lean, AI-native engineering environment with room to experiment and bring new technologies into production.
• Collaborative, fast-moving environment with autonomy and accountability.
• B2B contract.