Software Engineer, Machine Learning - Ads Infra and Ranking

Meta’s Ads organization builds the systems that help businesses of every size reach the people most likely to care about what they offer. At our core, we’re builders who care about shipping real value. Within Ads, the Infra and Ranking organization owns the technical foundation that makes this work at Meta’s scale: the ranking models that decide which ad is right for each moment; the retrieval and serving platforms that evaluate enormous candidate sets in milliseconds; and the underlying data, training, and inference infrastructure. All of this is done while maximizing compute efficiency, ensuring reliability and privacy, and using AI to speed up development.As a Software Engineer, Machine Learning in Ads Infra and Ranking, you will lead complex engineering projects that improve how production ML systems match people with relevant ads.You will translate model-quality opportunities into reliable software and measurable improvements, working across model development, data, and serving to balance relevance with the constraints of large-scale production systems.

Required Skills:

Software Engineer, Machine Learning - Ads Infra and Ranking Responsibilities:

1. Define and deliver ML engineering projects that improve ads ranking or retrieval, from problem framing and model evaluation through production rollout.
2. Develop models and supporting software, using data and analysis to diagnose quality issues and evaluate alternative approaches.
3. Partner with infrastructure and ML engineers on the data, feature, and serving dependencies needed to turn model improvements into production impact.
4. Design offline evaluations and online experiments that assess ad relevance, advertiser outcomes, and system performance.
5. Lead technical decisions and cross-functional execution for complex projects, making trade-offs explicit and building maintainable solutions.
6. Improve production quality through testing, code review, monitoring, and iteration across the model lifecycle.
7. Mentor engineers and help new team members ramp up in the relevant codebases and workflows, strengthening the team’s ability to deliver high-quality work.

1. Bachelor’s degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
2. Demonstrated experience driving change within an organization and leading complex technical projects
3. 8+ years of programming experience in a relevant language OR 4+ years experience with a PhD
4. Experience utilizing data and analysis to explain technical problems and provide detailed feedback and solutions

Preferred Qualifications:

Preferred Qualifications:

1. Experience developing and deploying ML models for advertising, ranking, retrieval, recommendation, or analogous large-scale prediction systems
2. Experience applying information retrieval and optimization methods to improve candidate relevance or ranking quality
3. Experience with ML frameworks such as PyTorch, TensorFlow, or Scikit-learn, including evaluation and integration into production software
4. Experience using offline analysis and online experimentation to evaluate model changes and understand quality, latency, or efficiency trade-offs
5. Experience leading engineering work across model development, data quality, and production serving dependencies
6. Demonstrated ability to integrate AI tools into ML development, evaluation, or debugging workflows with measurable efficiency or quality gains
7. Experience applying responsible AI practices, including risk assessment, bias mitigation, and quality and accuracy reviews, to production model development
8. Demonstrated ongoing AI skill development, including prompt/context engineering or agent orchestration, and evaluation of emerging technologies for engineering use
9. Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements)
10. Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)
11. Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies