Stellar Consulting Solutions, LLC
Lead Data Scientist (Retail)
⭐ - Featured Role | Apply direct with Data Freelance Hub
This role is for a Lead Data Scientist (Retail) in Pleasanton, CA, on a W2 contract for 10+ years of experience. Key skills include ETL, data science, and data quality. Experience in retail and recommender systems is essential.
🌎 - Country
United States
💱 - Currency
$ USD
-
💰 - Day rate
Unknown
-
🗓️ - Date
February 18, 2026
🕒 - Duration
Unknown
-
🏝️ - Location
On-site
-
📄 - Contract
W2 Contractor
-
🔒 - Security
Unknown
-
📍 - Location detailed
Pleasanton, CA
-
🧠 - Skills detailed
#"ETL (Extract #Transform #Load)" #Data Quality #Deployment #Data Science
Role description
Note: Only open on W2.
Job Description:
Role: Lead Data Scientist (Retail)
Location: Pleasanton, CA (Onsite-5days/week)
Contract role. (W2 Only)
Level: 3 (10+ Years)
Direct client requirement
Job Overview:
Retail domain.
Understand the frameworks used currently in terms of recommender system pipelines
Come up with ways to improve the current algorithms and pipelines, responsible for the end-to-end testing of the algorithm along with collaborating with the MLOps team to see the model through
Dataset Gathering - Collect Data
Transformer Architecture - 1. Customer Sequence Modeling, 2. Multi Modal and Variable Length Inputs
Offline Model - 1. Build Offline Model, 2. Hyperparameter Tuning
Build Online Inference Path - 1. Combine Offline with real time session features
Data Quality - 1. Deployment, 2. Success Metric Improvement
Note: Only open on W2.
Job Description:
Role: Lead Data Scientist (Retail)
Location: Pleasanton, CA (Onsite-5days/week)
Contract role. (W2 Only)
Level: 3 (10+ Years)
Direct client requirement
Job Overview:
Retail domain.
Understand the frameworks used currently in terms of recommender system pipelines
Come up with ways to improve the current algorithms and pipelines, responsible for the end-to-end testing of the algorithm along with collaborating with the MLOps team to see the model through
Dataset Gathering - Collect Data
Transformer Architecture - 1. Customer Sequence Modeling, 2. Multi Modal and Variable Length Inputs
Offline Model - 1. Build Offline Model, 2. Hyperparameter Tuning
Build Online Inference Path - 1. Combine Offline with real time session features
Data Quality - 1. Deployment, 2. Success Metric Improvement
