Fetch is a company focused on AI and data, utilizing an integrated ecosystem to turn data into impactful business and customer outcomes. They are seeking a Senior Machine Learning Engineer II to work on ad ranking systems, focusing on building and improving models that enhance ad selection and delivery at scale.
Responsibilities:
- Design, build, and improve machine learning models that power ad ranking, relevance, and optimization across the Fetch platform
- Implement and iterate on active learning strategies, including data sampling, error-driven retraining, and human-in-the-loop workflows to improve ranking quality
- Leverage LLMs to reduce model development and annotation effort, including synthetic data generation, assisted labeling, weak supervision, and error analysis for ranking and relevance tasks
- Own ML experimentation, offline and online evaluation, and production inference for assigned ad ranking components
- Partner closely with product, data, and platform teams to translate advertiser and user experience gaps into measurable ML improvements
- Maintain high standards for model performance, reliability, latency, and data quality in production ranking systems
- Use AI-assisted tools to accelerate development, experimentation, debugging, and analysis while maintaining strong engineering judgment
- Designing features and validating ideas with ChatGPT & Claude sandboxes
- Leveraging AI for code generation and technical prototyping
- Using AI assistants for systems architecture diagramming and design validation
Requirements:
- 6+ years of software engineering experience with a strong track record of building and maintaining production ML or data-driven systems
- Strong proficiency in Python for machine learning and data processing, with working knowledge of Go, and hands-on experience deploying low-latency models into production ranking or decisioning systems
- Experience with AWS and distributed systems, including building or operating scalable training pipelines and online inference services
- Practical experience applying LLMs to reduce model development and data labeling effort, including assisted labeling, synthetic data generation, weak supervision, or model error analysis
- Strong engineering judgment and systems mindset, with an emphasis on reliability, performance, and long-term maintainability of ranking or optimization systems
- Experience using AI-assisted development tools (e.g., GitHub Copilot, ChatGPT, or similar) to accelerate iteration while maintaining high code quality
- Ability to critically evaluate AI-generated outputs, debug complex issues, and validate correctness in production ML workflows
- Bachelor's or Master's degree in Computer Science, Machine Learning, or a related field, or equivalent practical experience
- Familiarity with modern AI tooling and frameworks such as AWS Bedrock, LangChain, vector databases, or similar orchestration technologies used in ML-powered decisioning systems
- Experience building and operating machine learning workflows involving large language models (LLMs), including prompt-driven systems and model-assisted pipelines
- Familiarity with orchestrating ML-driven decisions in high-throughput or low-latency environments, such as ranking, recommendation, or optimization systems
- Experience with applied machine learning for relevance, ranking, or personalization problems (e.g., feature engineering, model evaluation, or feedback loops)
- Experience working in small, fast-moving, cross-functional teams, partnering closely with product, data, and platform stakeholders