AI/Machine Learning Engineer

EPAM Systems; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

EPAM Systems seeks a proactive AI/ML Engineer to design, build, and optimize recommendation and ranking systems at scale in a modern cloud environment. You will develop models delivering personalized experiences and rigorously evaluate their performance.

Collaborate with cross-functional teams to deploy production ML pipelines using Python, SQL, Spark, and ML libraries (scikit-learn, PyTorch, LightGBM/XGBoost) on Databricks, with Git version control and MLflow for experiment tracking.

Qualifications

• 3+ years hands-on experience building recommendation or ranking models.
• Strong Python and SQL skills.
• Experience with Spark and large-scale data processing.
• Familiarity with ranking metrics like NDCG and recall@k.
• Experience with ML tooling (Databricks, MLflow, Git).

Responsibilities

• Design and build learning-to-rank and neural rankers for recommendations.
• Optimize models for multiple objectives using Pareto-front analysis.
• Conduct offline evaluation with ranking metrics like NDCG and recall@k.
• Address bias in logged data to ensure robust performance.
• Track experiments and manage models through their lifecycles.
• Deploy ML workflows on a cloud data platform and collaborate across teams.
• Maintain clean, version-controlled code using Git.

Skills

Python

SQL

Spark

Pandas

Polars

Git

MLflow

Databricks

PyTorch

LightGBM/XGBoost

Tools

Spark

Pandas

Polars

scikit-learn

PyTorch

LightGBM/XGBoost

MLflow

Databricks

Git

Job description

We are seeking a proactive AI/Machine Learning Engineer to join our team and help design, build, and optimize recommendation and ranking systems at scale. In this role, you will develop models that drive personalized experiences, rigorously evaluate their performance, and collaborate closely with cross-functional teams to deliver impactful machine learning solutions in a modern cloud environment.

Responsibilities

• Design and build recommendation and ranking models, including learning-to-rank, re-ranking, gradient-boosted, and neural rankers
• Optimize models for multiple objectives, including analyzing Pareto-fronts to balance competing goals
• Conduct offline evaluation of recommender systems using ranking metrics such as NDCG and recall@k
• Address position and selection bias in logged data to ensure robust model performance
• Apply statistical rigor through significance testing, confidence intervals, and A/B test and holdout design
• Process and analyze large-scale behavioral and clickstream data
• Develop, test, and maintain clean, version-controlled code using Git
• Track experiments and manage models throughout their lifecycle
• Deploy and manage machine learning workflows on a cloud data platform
• Collaborate proactively with cross-functional teams to deliver production-ready ML solutions

Requirements

• 3+ years of hands-on experience building recommendation or ranking models (e.g. learning-to-rank, re-ranking, gradient-boosted or neural rankers)
• Understanding of multi-objective optimization, including Pareto-front analysis
• Expertise in offline evaluation of recommenders using ranking metrics (e.g. NDCG, recall@k)
• Familiarity with position or selection bias in logged data
• Strong background in statistics, including significance testing, confidence intervals, and A/B test and holdout design
• Proficiency in Python and SQL
• Skills in large-scale data processing with Spark, pandas, and polars
• Competency in ML libraries such as scikit-learn, PyTorch, and LightGBM/XGBoost
• Experience working with behavioral or clickstream data
• Knowledge of experiment tracking and model management tools (e.g. MLflow)
• Familiarity with cloud data platforms, preferably Databricks
• Capability to write clean, tested, version-controlled code using Git
• English proficiency at an Upper-Intermediate level (B2) or higher
• Nice to have E-commerce or retail background
• Understanding of counterfactual or off-policy evaluation
• Familiarity with contextual bandits or online learning
• Experience with real-time model serving