Applied Scientist / Applied ML Engineer

The Role

We are looking for an Applied Scientist / Applied ML Engineer to design, build, and deploy machine learning models that power pricing, bidding, and decisioning on a cross-border payments platform. This role owns problems end to end, from formulation to production, and partners closely with Product and Backend Engineering.

Key Responsibilities

1. End-to-End ML Ownership - Own end-to-end ML solutions for pricing, bidding, and risk decisioning. - Formulate model objectives from first principles, including loss functions, constraints, and metrics, and implement them as production-grade services.

2. Experimentation & Iteration - Design and run experiments, including A/B tests and offline evaluations, and iterate with clear success metrics.

3. Production Monitoring - Monitor models in production, investigate regressions, and continuously improve performance.

Requirements

Essential

- 3-7 years of experience as an ML Engineer, Applied Scientist, or Data Scientist in industry.

- Bachelor's or Master's in Computer Science, Machine Learning, Mathematics, Statistics, or equivalent practical experience.

- Strong Python skills, including pandas, NumPy, and scikit-learn, plus at least one of PyTorch, TensorFlow.

- Strong ML fundamentals, including supervised and unsupervised learning, model evaluation, regularization, feature engineering, and statistics.

- Experience designing models from first principles and shipping them to production, in batch or real-time.

- Hands-on experience with data pipelines and ETL, such as Airflow or Spark, and strong SQL for feature engineering.

- Experience integrating ML into REST or gRPC APIs and microservice architectures.

- Ability to design and interpret experiments with statistical rigor.

- Strong problem-solving and communication skills, and the ability to work effectively in cross-functional and distributed teams.

Nice to Have

- Optimization, bandits, or decision-making under uncertainty, including dynamic pricing and bid optimization.

- Bidding, auctions, marketplace, or recommendation systems experience.

- Fintech background, including payments, cross-border, lending, trading, or risk and scoring.

- Fraud, AML, credit risk, or vendor risk scoring models.

- Model explainability tooling, including SHAP and feature importance, for auditable decisions.

- Cloud experience (AWS, GCP, or Azure), Docker, and MLOps basics such as model registry and CI/CD.

What We Offer

- Real ML in production with direct impact on pricing, risk, and vendor decisions at scale.

- Ownership of core models with room to influence architecture and roadmap.

- Strong engineering peers and complex optimization problems in a high-growth fintech.

Equal Opportunities Statement

Tolken is an equal opportunity employer. We are committed to creating an inclusive environment for all employees.