Senior Machine Learning Engineer – Scoring, Audience Models

This is a fully remote position, open to applicants in Europe.

📋 Description

• Take full ownership of account and lead scoring processes from start to finish, encompassing target definition, label design, feature engineering, model selection, and calibration.

• Develop lookalike and similarity systems to pinpoint high-potential accounts and verify them against adjusted baselines.

• Utilize Elasticsearch as a source for features and serving layer, incorporating aggregations, vector search, and indexed model scores.

• Design evaluations that prevent leakage, using decision-matched metrics such as lift, precision at k, calibration, and online experiments.

• Tackle challenges related to entity resolution, deduplication, data missingness, label noise, sampling bias, and feedback loops.

• Construct training and inference pipelines, feature storage, batch scoring, and near-real-time scoring systems.

• Integrate scoring systems with Node.js services.

• Monitor production models for drift and degradation, retraining them on a defensible schedule.

• Collaborate with product and engineering teams to display scores within the application.

• Clarify to customers the meaning and limitations of scores.

⛳️ Requirements

• A minimum of 4 years in machine learning or data science positions, including at least 2 years of experience deploying supervised models that informed actual decisions in production.

• A solid foundation in machine learning, deep learning, and advanced statistics, backed by a quantitative degree or equivalent rigorous training.

• Proficiency in the mathematics underlying machine learning, extending beyond mere API usage.

• In-depth knowledge of estimation and inference, sampling and selection bias, hypothesis testing and power analysis, regularization and bias/variance trade-offs, probability calibration, and the distinction between causal and correlational claims.

• Strong command of Python, scikit-learn, XGBoost/LightGBM, PyTorch or TensorFlow, pandas/Polars, NumPy, and SciPy.

• Experience in extracting and aggregating features from large document repositories at scale; readiness to engage directly with Elasticsearch query DSL and aggregations.

• Familiarity with ranking, propensity, similarity, recommendation, or churn/conversion modeling.

• Ability to defend model targets, label provenance, validation limitations, and post-launch failures.

• Experience in establishing ML foundations and infrastructure from an early stage.

• Adherence to engineering best practices including version control, testing, continuous integration, and containerization.

• Capability to deliver a scoring service to a Node.js team.

• Nice to have: Knowledge of Elasticsearch dense_vector and kNN search, significant_terms, rank_feature scoring, index design, and query performance optimization.

• Nice to have: Familiarity with B2B data, GTM, martech, adtech, CRM enrichment, and firmographic data providers.

• Nice to have: Experience with approximate nearest neighbor search using pgvector, Qdrant, or FAISS.

• Nice to have: Knowledge of learning-to-rank, graph/network modeling, MLOps tools, publications, competition achievements, or contributions to open-source applied ML projects.

🏝️ Benefits

• Comprehensive health insurance coverage.

• Flexible working hours and remote work options.

• Opportunities for professional development and continued education.

• Collaborative and innovative work environment.

• Competitive salary and performance-based incentives.