Applied Machine Learning Scientist

Key Skills

Apache Hadoop, C Programming, C++, Data science techniques, Java Programming, Machine learning techniques, MapReduce, Python Programming, PyTorch, R Programming, Scala Programming, SQL, TensorFlow

Job Description

The personalization effort is a part of the Data Science team at Teladoc Health that works closely with product managers, engineering, and operations to build, ship, and maintain machine learning models and pipelines to provide members an experience that is engaging and improves clinical outcomes.

This is an opportunity to use technical rigor to apply machine learning to real-world business problems; and engineer, deploy, measure and iterate ML in production, for every Teladoc Health member.

Responsibilities

• Build production-ready machine learning models to identify and personalize recommendations that improve member engagement and lead to clinical outcomes.
• Formulate and solve machine learning problems using diverse data using Deep Reinforcement Learning, Learning to Rank, Matrix Factorization, NLP, Contextual Bandits, etc.
• Formulate hypothesis, design, analyze, and run offline (policy evaluation) and online experiments to measure, iterate, and improve performance of algorithms, product features, and member communications.
• Interpret the results of your work for clinical, product, and business decision-makers.
• Collaborate closely with product management and engineering teams to discover and distill requirements into problem definitions, product features, and architecture.

Candidate Profile

• Self-driven person, with a proven track record using machine learning to solve challenging business, technical, and data engineering problems.
•  Expertise in machine learning theory, as well as practical tricks for working with and delivering machine learning models including reinforcement learning, recommender systems, deep learning, collaborative filtering, NLP, predictive modeling, causal modeling, contextual bandits.
• Excellent data analysis skills and bias to deliver, measure, and iterate using experimentation and statistical analysis.
• Depth of experience in Python, PyTorch, Tensorflow, and at least one of the following: Spark, SQL, and/or Hadoop.
• Experience developing, prototyping, and deploying machine learning and personalization models.
• Familiarity with the entire ML algorithm lifecycle (modeling approach ideation, data exploration, training, evaluation, tuning).
• Willingness to learn new platforms and tools, as well as propose and help the team adopt new tools.
• Great active listening skills to infer product needs and underlying context.
• Ability to collaborate effectively with peers, and respect for member privacy