11 hours ago
Responsibilities
- Design, build, and improve machine learning models for ad ranking, relevance, personalization, and optimization.
- Implement active learning strategies, including data sampling, error-driven retraining, and human-in-the-loop workflows.
- Apply LLMs to synthetic data generation, assisted labeling, weak supervision, and ranking error analysis.
- Own ML experimentation, offline and online evaluation, and production inference for assigned ranking components.
- Build and operate feature pipelines, training workflows, and low-latency inference services.
- Partner with product, data, and platform teams to translate advertiser and user-experience gaps into measurable ML improvements.
- Maintain model performance, reliability, latency, and data quality in production.
- Use AI-assisted development tools for prototyping, debugging, architecture validation, and analysis while evaluating output correctness.
Requirements
- 5+ years of software engineering experience building and maintaining production ML or data-driven systems.
- Strong proficiency in Python for machine learning and data processing.
- Working knowledge of Go and experience deploying low-latency models into production ranking or decisioning systems.
- Experience with AWS and distributed systems, including scalable training pipelines and online inference services.
- Practical experience applying LLMs to model development and data-labeling workflows.
- Strong engineering judgment and systems thinking focused on reliability, performance, and maintainability.
- Experience with AI-assisted development tools such as GitHub Copilot or ChatGPT.
- Ability to critically evaluate AI-generated outputs, debug complex issues, and validate production ML workflows.
- Bachelor’s or master’s degree in Computer Science, Machine Learning, or a related field, or equivalent practical experience.
- Familiarity with AWS Bedrock, LangChain, vector databases, or similar AI orchestration technologies is preferred.
- Experience with LLM workflows, prompt-driven systems, ranking, recommendation, optimization, relevance, personalization, feature engineering, model evaluation, or feedback loops is preferred.
Categories
About Fetch
Fetch builds a consumer rewards app where users earn points by scanning receipts and redeem them for gift cards, while brands use its SKU-level, retail-agnostic purchase data for targeted, outcomes-based advertising and measurement. The privately held company, founded in 2013, processes over 13 million receipts daily, creating visibility into more than $200 billion in gross merchandise value. Its platform has awarded over $1 billion in points and operates a hybrid-remote workplace.