Design high-performance machine learning pipelines using both online and offline feature engineering

Implement advanced machine learning models leveraging Python and TensorFlow

Optimize inference workflows for low-latency, real-time data like player telemetry

Orchestrate machine learning processes with MLflow

Integrate datasets through ETL/ELT workflows on Databricks

Monitor, debug, and refine production ML systems for optimal performance

Automate scalable feature engineering and model deployment solutions

Collaborate with interdisciplinary teams to align machine learning with overall system goals

Utilize Databricks for effective dataset management and computational processes

Establish best practices for scalable and maintainable machine learning systems

3+ years of experience creating machine learning pipelines and products

Proficiency in Databricks, MLflow, TensorFlow

Skills in Python for machine learning and data engineering workflows

Background in ETL/ELT platforms, with competency in large-scale integrations

Understanding of real-time data processing and low-latency system requirements

Capability to structure and improve online and offline feature engineering workflows

Knowledge of ML model lifecycle management and tuning pipeline performance

Competency in designing scalable, efficient ML solutions for complex scenarios

English level of minimum B2 (Upper-Intermediate) to ensure effective communication

Expertise in recommender systems for advancing content personalization and discovery

Capability to deploy machine learning processes on AWS infrastructure

Proficiency in leveraging real-time analytics or telemetry-focused data solutions