Machine Learning Engineer

Comcast Corporation

Irvine (CA)

Hybrid

USD 143,000 - 190,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Comcast Corporation in Irvine, CA seeks a seasoned Machine Learning Engineer to design, train, and deploy ML models powering personalized recommendations. The role spans modeling, data pipelines, evaluation, and cross-team integration in a hybrid office setting.

Expect 5–7 years of experience with Python/R, BigQuery, and databases. You’ll mentor juniors and drive the core recommendation system across teams with a focus on performance and scalability.

Qualifications

3+ years of experience using statistical languages (Python, R, etc.).
3+ years of experience manipulating big data (BigQuery, etc.).
3+ years of experience operating databases (MySQL, PostgreSQL, Oracle, MongoDB).
Experience with clustering, decision tree learning, and artificial neural networks.
Experience with advanced statistical techniques and concepts such as regression and statistical tests.
Excellent written, drawing, and verbal communication for cross-team coordination.
Office-based in Irvine, CA, 4 days/week in office and 1 day remote.

Responsibilities

Develop and improve machine learning algorithms for integration across products and applications.
Lead training of machine learning models, including validation and deployment into production systems.
Create and maintain data pipelines for ingestion, validation, cleaning, and monitoring.
Produce documentation and technical requirements, including evaluation plans and reports.
Collaborate with cross-functional teams to provide technical solutions for complex issues.
Provide guidance and mentorship to junior engineers and set a technical example.

Skills

Collaboration

Algorithms

Recommendation Engines

Business Problems

Education

Bachelor's Degree

Job description

XUMO (Comcast) is seeking a highly experienced Machine Learning Engineer to design, train, and deploy machine learning models that power recommendation capabilities. This hybrid role in Irvine, CA focuses on personalization algorithms built on large-scale data, with responsibilities spanning modeling, evaluation, data pipelines, and cross-team integration.

Responsibilities

Develop and improve machine learning algorithms for integration across products and applications, aligned to specifications and data pipeline architectures.
Lead training of machine learning models, including validation and deployment into production systems.
Create and maintain data pipelines that support efficient data ingestion, validation, cleaning, and ongoing monitoring.
Produce documentation and technical requirements, including evaluation plans, white papers, and reports.
Contribute to patents, Application Programming Interfaces (APIs), and other intellectual property.
Assess machine learning solutions from internal and external partners by leading testing and assessment initiatives.
Run deep-dive case studies and compile findings to inform product development and testing strategies.
Design proof of concept solutions and direct studies that support future product or application advancement.
Collaborate with cross-functional teams to provide technical solutions for complex issues tied to assigned projects.
Provide guidance and mentorship to junior engineers and set a technical example within the team.
Develop and train sophisticated machine learning algorithms and implement the core recommendation system to increase product engagement through collaboration with multiple systems.
Analyze big data to generate algorithmic insights.
Work with product and operations teams to translate business requirements into algorithmic solutions, documenting model architectures and logic.
Rapidly prototype new recommendation concepts and algorithms, validating mathematical approaches and transitioning experimental models into production-ready code.
Implement, tune, and scale advanced machine learning models and multi-algorithm A/B testing logic to develop the core intelligence of the recommendation system.
Partner with backend and client engineering teams to integrate models, prioritize algorithmic enhancements, and define approaches for model serving and latency reduction.
Create technical documentation covering algorithm behavior, model dependencies, and requirements for system integration with the recommendation engine.
Drive decisions on model selection, hyperparameter optimization, and feature engineering to address complex business problems and improve personalized content delivery.
Engineer feature sets and training data schemas optimized for recommendation algorithm training and serving.
Execute offline evaluations and online A/B tests, producing insights into performance against established baselines and benchmarks.
Drive results and growth, and support a culture of inclusion in day-to-day work and leadership.

Requirements

3+ years of experience using statistical computer languages (Python, R, etc.).
3+ years of experience manipulating big data (BigQuery, etc.).
3+ years of experience operating databases (MySQL, PostgreSQL, Oracle, MongoDB).
Experience and knowledge of developing multiple machine learning techniques including clustering, decision tree learning, and artificial neural networks, including real-world advantages and drawbacks.
Experience and knowledge of advanced statistical techniques and concepts such as regression, properties of distributions, statistical tests, and appropriate application.
Strong problem-solving skills with emphasis on product development.
Excellent written, drawing, and verbal communication skills for coordinating across teams.
Strong leadership in designing and implementing approaches for new features and problem solving.
Self-starter capable of producing high-quality output with minimal supervision.
Aggressive learner for new technologies and techniques.
Role location: office-based in Irvine, CA, 4 days/week in office and 1 day remote.

Technologies

Python, R
BigQuery
MySQL, PostgreSQL, Oracle, MongoDB
Big data
clustering, decision tree learning, artificial neural networks, regression, statistical tests
Google Cloud, AWS, Azure
Spark
Linux-based operating system, CentOS, OSX
A/B testing
machine learning frameworks

Desirable Experiences