[Hiring] Machine Learning Engineer @NextGen Commerce

Role Description

Ford Motor Company is seeking a Senior Data Scientist to support its Global Data, Insights & Analytics Quality Analytics team. This consultant will help expand an agentic AI framework that recommends assignments for vehicle quality issues. The solution combines machine learning similarity-based retrieval with LLM-powered semantic ranking and integrates structured and unstructured automotive data. The role will focus on improving model accuracy, expanding coverage across Vehicle Function Groups, and maintaining human review for all assignment decisions.

Responsibilities

• Diagnose the causes of low assignment accuracy, including data sparsity, duplicate records, feature relevance, and ranking behavior.
• Implement Vehicle Function Group-specific model improvements through feature selection, retrieval threshold tuning, and semantic ranking prompt refinement.
• Integrate warranty claims, diagnostic signals, connected-vehicle data, issue descriptions, and other structured and unstructured sources into governed data pipelines.
• Deliver ranked recommendations through existing client applications while ensuring assignments remain subject to human review.
• Support the onboarding of additional Vehicle Function Groups to achieve full coverage for assignment recommendations.
• Develop a feedback-learning process that uses reviewer corrections to refine retrieval thresholds and ranking prompts.
• Implement detection capabilities for noisy, duplicate, and near-duplicate records, including merge recommendations.
• Contribute to dashboards tracking coverage, model accuracy, acceptance rates, and time-to-categorization trends.
• Participate in weekly technical working sessions, bi-weekly product status reviews, and monthly stakeholder reviews.

Qualifications

• Bachelor's or Master's degree in Data Science, Computer Science, Statistics, Engineering, or a related quantitative discipline.
• 6+ years of hands-on data science experience, including deploying machine learning models into production environments.
• Advanced Python skills using libraries such as pandas, NumPy, and scikit-learn.
• Experience with feature engineering and feature selection methodologies.
• Experience developing similarity-based retrieval models, recommendation systems, or other high-cardinality matching solutions.
• Practical experience designing and refining prompts for LLM-based semantic ranking or classification solutions.
• Experience building data pipelines that combine multiple structured and unstructured sources into a unified feature set.
• Working knowledge of Google Cloud Platform (GCP) for data pipelines, model development, and deployment.
• Experience defining evaluation frameworks and tracking metrics such as model accuracy, acceptance rate, and coverage.
• Strong written and verbal English communication skills for daily collaboration with US-based technical and business stakeholders.

Nice-to-Haves

• Experience in automotive quality, warranty, manufacturing, or related analytics.
• Experience developing human-in-the-loop systems that use reviewer feedback to retrain or retune models.
• Experience with duplicate or near-duplicate record detection and merge-recommendation logic.
• Experience working with agentic AI or multi-stage retrieval-and-ranking architectures.
• Familiarity with Jira or similar issue-tracking platforms.

Interview Information

Candidates should be prepared to discuss production machine learning deployments, similarity-based retrieval or recommendation systems, LLM prompt refinement, data pipeline design, model evaluation frameworks, and experience collaborating with US-based stakeholders in English.