Senior AI/ML Engineer

Day to Day:

An employer is looking for a Senior AI/ML Engineer for a remote, 6-month contract (with very likely extensions) opportunity. The client is a large, retail chain and the Senior AI/ML Software Engineer will help accelerate the evolution of our A/B Testing Platform by integrating advanced LLM-driven capabilities. This role will focus on transforming experimentation data into actionable intelligence—enabling automated test recommendations and enhanced experiment analysis at scale.

This role will be a key part of our A/B Testing Platform team to design and build systems that leverage large language models (LLMs) to unlock deeper insights from our experimentation data. This is a high-impact role at the intersection of ML engineering, data engineering, and platform development, directly influencing the effectiveness of experimentation across Kroger’s eCommerce ecosystem.

This role directly accelerates how we learn from experimentation—shifting from manual analysis to AI-driven insight generation at scale. By embedding intelligence into our A/B testing platform, you will help unlock faster decision-making, improved customer experiences, and measurable business impact across the client’s digital ecosystem.

Key Responsibilities:

LLM-Driven Experimentation Intelligence

• Design and implement systems that leverage LLMs to:
• Generate experiment recommendations (e.g., new test ideas, optimization opportunities)
• Provide automated analysis and summarization of test results
• Develop prompt strategies, evaluation frameworks, and feedback loops to continuously improve LLM output quality
• Integrate structured and unstructured experimentation data into LLM-ready formats

Data Engineering & Pipeline Development

• Build and maintain scalable data pipelines to ingest, transform, and store experimentation data
• Structure and curate datasets to optimize for LLM consumption and analytical accuracy
• Ensure data quality, lineage, and governance across experimentation datasets

Backend & Platform Development

• Develop backend services (Node.js / Python) to:
• Orchestrate LLM interactions via AI Gateway
• Enable efficient querying, caching, and retrieval of insights
• Support real-time and batch inference workflows
• Build APIs that power both internal services and user-facing applications

Data Modeling & Insight Delivery

• Design data models that enable efficient storage, retrieval, and visualization of experiment insights
• Collaborate with front-end teams (React) to surface insights in intuitive, actionable formats
• Implement mechanisms for storing and reusing generated insights and recommendations

Cross-Team Collaboration

• Partner with A/B Testing Platform engineers to integrate AI capabilities into existing services
• Work with product and engineering stakeholders to align on experimentation strategy and use cases
• Contribute to platform architecture decisions and long-term AI/ML roadmap

Must-Haves:

• 6+ years of experience in software engineering, ML engineering, or data engineering
• Strong programming skills in Python and/or Node.js
• Experience building data pipelines and distributed systems
• Hands-on experience with LLMs and AI systems (e.g., prompt engineering, embeddings, RAG, fine-tuning concepts)
• Experience designing and building backend services and APIs
• Strong understanding of data modeling, storage, and retrieval systems
• Experience working in cloud environments (e.g., GCP preferred)

Plusses:

• Experience building AI-powered analytics or recommendation systems
• Familiarity with experimentation platforms, A/B testing, or product analytics
• Experience with:
• Feature stores or ML data platforms
• Vector databases and semantic search
• Observability and evaluation frameworks for LLM outputs
• Experience integrating AI/ML capabilities into production platforms at scale
• Frontend exposure (React) to better collaborate on insight delivery

What Success Looks Like

• Automated generation of high-quality experiment recommendations adopted by product teams
• Significant improvement in speed and depth of experiment analysis
• Reliable, scalable pipelines that transform experimentation data into LLM-ready insights
• Seamless integration of AI capabilities into the A/B Testing Platform ecosystem

Compensation:

Up to $75/hr.

Exact compensation may vary based on several factors, including skills, experience, and education.

Employees in this role will enjoy a comprehensive benefits package starting on day one of employment, including options for medical, dental, and vision insurance. Eligibility to enroll in the 401(k) retirement plan begins after 90 days of employment. Additionally, employees in this role will have access to paid sick leave and other paid time off benefits as required under the applicable law of the worksite location.