Senior ML Engineer

Key Skills

Agile methodologies, Azure, Confluence, Data science techniques, Databricks, Deep Learning, Design, Docker, Effective communication skills, ETL frameworks, Jenkins, JIRA, Machine learning techniques, MLflow, Python Programming, Scala Programming

Job Description

PepsiCo Data & Analytics Overview:

With data deeply embedded in our DNA, PepsiCo Data & Analytics transforms data into consumer delight. We build and organize business-ready data that allows PepsiCo’s leaders to solve their problems with the highest degree of confidence. Our platform of data products and services ensures data is activated at scale. This enables new revenue streams, deeper partner relationships, new consumer experiences, and innovation across the enterprise.

The Data Science Pillar in D+A will be the organization where Data Scientist and ML Engineers report to in the broader D+A Organization. Also DS will lead, facilitate and collaborate on the larger DS community in PepsiCo. DS will provide the talent for the development and support of DS component and its life cycle within D+A Products. And will support “pre-engagement” activities as requested and validated by the prioritization framework of D+A.

Position Overview:

Your role will be to be part of growing team based in Dallas, to create and support global digital developments for PepsiCo. These developments will be focused on Integrated Business Planning with the focus on creating high quality demand forecasts, demand decomposition metric and new product forecasting as specified in the PepsiCo’s Integrated Business Planning program. You will create these forecasts and related analytical outputs by using advanced forecasting, experimentation and deployment toolkits.

You will be part of a collaborative interdisciplinary team around data, where you will be responsible of our continuous delivery of statistical/ML models. You will work closely with process owners, product owners and final business users. This will provide you the correct visibility and understanding of criticality of your developments.

You will be an internal ambassador of the team’s culture around data and analytics. You will provide stewardship to colleagues in the areas that you are an specialist or you are specializing.

Responsibilities

• Active contributor to code development in projects and services, leading other ML Engineers and data scientists and coaching them on best methods for feature engineering, data processing scalability and model deployment.
• Act as contributor in innovation activities.
• Work with data scientists, IBP process leads and BU subject matter experts to help identify incoming data clusters to achieve maximum forecasting performance metrics (high accuracy, low bias and good trend shapes).
• Partner with data scientist working on discovery, prototypes and pilot. Focus on translating business operation models to ML and statistical model ready analytical data sets (MRD).
• Partner with the PepsiCo Forecasting Engine Build team (in the same IBP DS organization) to design, implement and test pre-processing and post-processing modules to improve demand forecasts.
• Use data in the Enterprise data foundation and any experimental data to accomplish this preparation of MRD.
• Partner with data engineers regarding data pipelines and data versioning.
• Occasionally, coordinate work activities with IT services and vendors as required.
• Build, deploy or publish machine learning models and data preprocessing pipelines that run efficiently in cloud pipelines.
• Help drive optimization, testing, and tooling to improve quality (unit tests).
• Monitor model performance (model decay), working with data scientists assessing bias and fairness.
• Prototype new approaches and build solutions at scale.
• Support large-scale experimentation done by data scientists.
• Research in state-of-the-art methodologies and techniques for feature engineering, model data preprocessing and performance of the pipelines to accommodate service level agreements for the larger North American Business Units.
• Create documentation for learnings and knowledge transfer.
• Create and audit reusable packages or libraries.

Qualifications

• 4+ years working in a team to deliver production level analytic solutions
• 4+ years’ experience in ETL and/or data wrangling
• 4+ years’ experience in Statistical/ML techniques to solve supervised (regression, classification) and unsupervised problems. Experiences with Deep Learning are a plus
• 4+ years’ experience in developing business problem related statistical/ML modeling with industry tools with primary focus on Python or Scala development
• Strong communications and organizational skills with the ability to deal with ambiguity while juggling multiple priorities
• Experience with Agile methodology for team work and analytics ‘product’ creation Fluent in Jira, Confluence
• Fluent with Azure cloud services. Certification is a plus
• Fluent in git (version control)
• Fluent in Docker
• Fluent in Jenkins
• Fluent with design and management of APIs
• Experience with K8s is a plus
• Experience with working with FAIR data is a plus
• Experience with Responsible AI is a plus
• Experience with distributed systems is a plus
• Experience with Databricks and Mlflow is a plus
• Experience with ELK is a plus
• Experience with ML security is a plus