Senior Machine Learning Engineer – Recommendation Systems (Remote, LATAM)
Remote | Full-time | Contractor | LATAM (Colombia, Argentina, Peru, Chile, Uruguay, Costa Rica, Ecuador, Panama, Dominican Republic, Guatemala, Honduras, Nicaragua, El Salvador, Bolivia, Paraguay) | English required
About the Role
We’re hiring a Senior Machine Learning Engineer to join a data enablement team focused on personalization, recommendation, and ranking at scale. You’ll design and ship production-grade ML systems that surface relevant content to users across a large auction and marketplace platform. This is a high-impact, research-meets-engineering role where your models directly shape the user experience.
Responsibilities
- Design and develop recommendation algorithms using collaborative filtering, content-based filtering, and hybrid approaches to surface relevant auction items to bidders
- Build and optimize learning-to-rank models that re-rank search results based on user preferences, behavioral signals, and contextual features
- Develop personalization systems that adapt to individual user interests, browsing patterns, and bidding history across multiple auction categories
- Build classification and embedding models to represent product taxonomy and enable semantic similarity matching
- Collaborate with engineering and MLOps teams to integrate ML models into production systems and APIs
- Design and run A/B tests to measure the causal impact of recommendation strategies and derive actionable insights
- Apply computer vision techniques to enhance visual similarity recommendations
- Track scientific advancements in recommender systems and contribute to technical publications when applicable
Requirements
- MSc or PhD in Machine Learning, Data Science, Computer Science, Statistics, or a related field
- Strong Python expertise and hands-on experience with Pandas, NumPy, Scikit-learn, TensorFlow, or PyTorch
- Solid understanding of recommendation system architectures: collaborative filtering, content-based filtering, and hybrid approaches
- Experience with learning-to-rank algorithms (RankNet, LambdaMART, LambdaRank) applied to recommendation ranking and re-ranking
- Experience with deep learning for recommendations: neural networks, embeddings, two-tower models, or transformer-based architectures
- Knowledge of personalization and feature engineering: user profiling, behavioral modeling, implicit feedback, cold-start, and sparse data handling
- Experience evaluating recommenders with Precision@K, Recall@K, NDCG, MRR, diversity, and coverage metrics; A/B testing and experimental design
- Strong communication and collaboration skills; ability to work effectively in cross-functional teams
- English proficiency required
Nice to Have
- Experience with vector databases or large-scale embedding systems (Elastic, Milvus, Pinecone)
- Familiarity with computer vision models for visual similarity or image-based recommendations
- Knowledge of multi-armed bandit algorithms and exploration-exploitation strategies
- Experience with session-based or sequence-aware recommendation models (RNNs, transformers)
- Understanding of fairness, diversity, and serendipity in recommendation systems
- Background in marketplace or e-commerce recommendation systems