Staff Machine Learning Engineer, Retrieval & Targeting

Description

The company runs a large online community platform with over 100,000 active communities and about 130 million daily active unique visitors.

The Ads Retrieval ML team builds the models that pick which advertising campaigns and ads are eligible to compete for each user. Retrieval comes first in the ads delivery funnel, before ranking and auction. The work spans several objectives, placements, and geographies, and draws on representation learning, candidate generation, nearest-neighbor search, behavioral and contextual signals, and offline and online experiments.

This is a Staff Machine Learning Engineer role leading technical direction for the Retrieval and Targeting ML team. You will shape retrieval models and modeling practices meant to improve relevance, advertiser results, and user experience at very large scale. The role is applied ML focused on retrieval and end-to-end product impact. You stay hands-on with data, objective design, model development, evaluation, experiments, and launches while guiding other engineers.

Responsibilities

• Set the technical direction and multi-year roadmap for ads retrieval modeling, working with engineering, product, data science, and ads stakeholders.
• Design, build, and launch candidate-generation and retrieval models for campaigns and ads across the company's advertising surfaces.
• Use modern methods such as two-tower architectures, representation learning, embeddings, sequence models, graph-based methods, and other deep learning techniques where they add real product value.
• Improve the retrieval stack, including objectives, labels, sampling, hard-negative mining, feature design, embedding generation, candidate filtering, and retrieval depth.
• Work with approximate nearest-neighbor and vector retrieval systems, weighing recall, relevance, freshness, diversity, coverage, latency, and cost.
• Set up strong evaluation practices that tie retrieval metrics such as recall, precision, candidate coverage, calibration, and downstream lift to ads and user results.
• Lead offline analysis and online experiments, make sense of unclear results, and turn findings into the next model iteration.
• Work with downstream ranking, ads platform, auction, measurement, and product teams so retrieval models fit well across the full ads funnel.
• Write design documents, review code and model changes, and set high standards for modeling, testing, observability, and production ownership.
• Mentor ML engineers and build the team's skills in retrieval, recommendation, and representation learning.

Requirements

• 7+ years of industry experience, including substantial time building and shipping applied ML products.
• Deep experience with information retrieval, candidate generation, recommender systems, ranking, or similar relevance problems.
• Solid understanding of retrieval modeling, including DNNs, embeddings, two-tower or dual-encoder models, approximate nearest-neighbor search, and multi-stage retrieval.
• Deep experience training, evaluating, debugging, and deploying deep learning models in TensorFlow, PyTorch, or similar frameworks.
• A record of owning ML projects from problem framing and data preparation through offline evaluation, online testing, launch, and iteration.
• Strong skill in experiment design and model evaluation, including how offline retrieval metrics map to business and user metrics.
• Experience with large-scale behavioral, contextual, or content data and complex feature pipelines.
• Strong software engineering fundamentals and the ability to write clear, reliable, maintainable production code.
• Technical leadership experience: setting direction, leading complex projects, influencing partner teams, and mentoring engineers.
• Excellent written and verbal communication, able to explain complex modeling choices to both technical and non-technical audiences.
• Preferred: experience with ads retrieval, ads ranking, ad targeting, ad serving, recommendation, search relevance, or marketplace optimization.
• Preferred: experience modeling user, content, campaign, or ad interactions with sequential, graph, or multimodal signals.
• Preferred: experience linking retrieval gains to downstream ranking, auction, conversion, revenue, or user-experience outcomes.
• Preferred: experience in ads marketplaces at peer companies.
• Preferred: publications, patents, or industry contributions in applied ML or ranking systems.
• Preferred: experience with sequential modeling, such as RNNs or Transformers.

Conditions

This posting may cover more than one career level.

The role includes base salary plus restricted stock units and, depending on the position, possibly a commission. U.S.-based employees also get medical, dental, and vision insurance, a 401(k) with employer match, generous vacation time, and parental leave.

Base salary ranges are shared for all US-based postings in every state. Ranges are set by function, level, and country, benchmarked against similar growth-stage companies. Final offers depend on factors such as skills, depth of experience, and relevant licenses or credentials, and may fall outside the range.

The base salary range is $230,000 - $322,000 USD.

In select roles and locations, interviews may be recorded, transcribed, and summarized by AI. You can opt out before any scheduled interview.

The company is an equal opportunity employer and provides reasonable accommodations for qualified individuals with disabilities and disabled veterans during the application process. Tell your recruiter if you need an accommodation during interviews.

Work is 100% remote, or you can choose one of four offices for hybrid or onsite work: New York, San Francisco, Los Angeles, or Chicago.

Benefits

• Comprehensive healthcare and income replacement programs.
• 401(k) with employer match.
• Global benefit programs covering workspace, professional development, and caregiving support.
• Family planning support.
• Gender-affirming care.
• Mental health and coaching benefits.
• Flexible vacation and paid volunteer time off.
• Generous paid parental leave.