Staff Machine Learning Engineer, Search Ranking

Snap•Palo Alto, CA

2d•Hybrid

About The Position

Snap Inc. is a technology company focused on improving communication and daily life through its camera-centric products. The company operates Snapchat, Bitmoji, and other digital services. Snap's Engineering teams build technically sophisticated products used by hundreds of millions of users globally. They are committed to their values, moving fast with precision, and prioritizing privacy. This role is for a Staff Machine Learning Engineer to lead the development of next-generation Search ranking systems, focusing on machine learning models that determine the relevance, quality, personalization, and utility of search results at scale.

Requirements

Strong machine learning fundamentals, including supervised learning, ranking models, embeddings, deep learning, optimization, evaluation, and experimentation.
Strong programming skills in Python, C++, Java, Scala, or similar languages.
Experience with large-scale data processing and ML infrastructure, such as Spark, Flink, Beam, TensorFlow, PyTorch, JAX, or similar tools.
Ability to take ML models from research or prototyping into large-scale production systems.
Strong understanding of online experimentation, A/B testing, metric design, model debugging, and tradeoff analysis.
Proven ability to lead complex technical projects across multiple teams.
Excellent communication skills and ability to explain complex ML concepts to technical and non-technical stakeholders.
Bachelor's Degree in a relevant technical field such as computer science or equivalent years of practical work experience.
8+ years of post-Bachelor’s machine learning experience; or Master’s degree in a technical field + 7+ year of post-grad machine learning experience; or PhD in a relevant technical field + 4 years of post-grad machine learning experience.
Experience developing machine learning models for relevance ranking, personalization, intent understanding, and/or engagement optimization.
Experience with large-scale data processing and ML infrastructure, such as Spark, Flink, Beam, TensorFlow, PyTorch, JAX, or similar tools.

Nice To Haves

Advanced degree in Computer Science, Machine Learning, Statistics, Mathematics, Information Retrieval, or a related field.
Direct experience building Search ranking systems, including query understanding, retrieval, ranking, re-ranking, relevance modeling, or result blending.
Experience with ads ranking, recommendation ranking, feed ranking, marketplace ranking, or content discovery systems.
Experience with learning-to-rank methods such as LambdaMART, pairwise/listwise ranking losses, neural ranking models, or transformer-based rankers.
Experience with candidate generation, retrieval models, ANN search, embeddings, vector search, or two-stage ranking architectures.
Experience optimizing ranking systems for multiple objectives, including relevance, engagement, quality, diversity, freshness, long-term user value, and monetization.
Experience with LLMs, foundation models, semantic search, natural language understanding, or retrieval-augmented generation.
Experience building low-latency ML serving systems and improving production model reliability.
Track record of publishing, patenting, or otherwise advancing the state of the art in search, ranking, recommendations, ads, or applied ML.

Responsibilities

Lead the design and development of machine learning models for Search ranking, including relevance ranking, personalization, result quality, intent understanding, and engagement optimization.
Own major ranking initiatives from problem definition through experimentation, launch, and iteration.
Develop and improve ranking models using techniques such as learning-to-rank, deep retrieval, neural ranking, sequence models, embeddings, multi-task learning, calibrated prediction, and large-scale feature engineering.
Build ranking systems that balance multiple objectives, such as relevance, user satisfaction, freshness, diversity, fairness, safety, latency, and business goals.
Partner with product managers, data scientists, and engineers to define success metrics, experimentation strategy, and long-term ranking roadmap.
Analyze user behavior, search logs, query-result interactions, and model performance to identify opportunities for improvement.
Design robust offline evaluation, online experimentation, and model monitoring frameworks.
Improve feature pipelines, training infrastructure, serving systems, and model iteration velocity.
Provide technical leadership across teams, influence architecture decisions, and mentor engineers working on ML ranking systems.
Stay current with advances in search, recommendation systems, ads ranking, generative AI, LLM-based ranking, and retrieval-augmented systems.