Senior ML Engineer — Real-Time Ad Ranking & Optimization

Fetch; Northern (KY); Hybrid; USD 150,000 - 210,000; Full time

Job summary

Fetch is seeking a Machine Learning Software Engineer to join its Ads Platform team. This role focuses on building ranking, relevance, and optimization models that drive ad selection and delivery at scale.

You will collaborate with product, data, and platform teams to develop feature pipelines, model training workflows, and low-latency serving infrastructure. The role emphasizes reliability, performance, and measurable improvements in advertiser performance and user engagement.

Qualifications

• 5+ years of software engineering experience with production ML or data-driven systems.
• Proficiency in Python for ML and data processing; working knowledge of Go.
• Experience with AWS and distributed systems; scalable training pipelines and online inference services.
• Practical experience applying LLMs to reduce development and data labeling effort.
• Strong engineering judgment with reliability and performance focus.
• Experience with AI-assisted development tools (e.g., Copilot, ChatGPT).

Responsibilities

• Design, build, and improve ML models for ad ranking, relevance, and optimization.
• Iterate on active learning strategies to improve ranking quality.
• Leverage LLMs to reduce development and annotation effort.
• Own ML experimentation, offline/online evaluation, and production inference.
• Collaborate with product, data, and platform teams to translate gaps into ML improvements.
• Maintain high standards for model performance, reliability, latency, and data quality.
• Use AI-assisted tools to accelerate development and debugging.

Skills

Python

Go

AWS

Distributed systems

LLMs

Model deployment

Active learning

AI tooling

Data labeling

Education

Bachelor's or Master's in CS/ML

Tools

GitHub Copilot

LangChain

Bedrock

Vector databases

Job description

Fetch is seeking a Machine Learning Software Engineer to join its Ads Platform team. This role focuses on building ranking, relevance, and optimization models that drive ad selection and delivery at scale.

You will collaborate with product, data, and platform teams to develop feature pipelines, model training workflows, and low-latency serving infrastructure. The role emphasizes reliability, performance, and measurable improvements in advertiser performance and user engagement.