The posting
About NewsBreak
Local life runs on local information. What happened down the street? Who can fix this? Where should we go tonight? NewsBreak started in 2015 to answer these questions, and today more than 40 million people a month rely on us to follow what’s going on in their zip code.
Three platforms with one vision: powering local life. Led by founder and CEO Jeff Zheng, NewsBreak is our local life and news platform; Nearby AI connects people with local businesses; and NDot AI helps publishers and creators grow and earn.
Building for the long term. A $115 million Series C made us a unicorn in 2021, and we keep investing in our people. We’re Great Place to Work® certified and named to Fast Company’s Best Workplaces for Innovators (2025) and Fortune’s Best Workplaces in the Bay Area™ (2026).
Everyone makes an impact. Whether you write code, shape products, tell our story, or run the business, we want people who own projects end to end, stay curious, and speak up. Join us.
Learn more at: NewsBreak, Nearby AI, NDot AI
About the team
The User Signal team sits at the heart of our in-house advertising platform. We collect, process, and activate user signals — behavioral events, contextual data, engagement history, and identity signals — and turn them into the features and audiences that power ads targeting, bidding, and ranking across the company's ad stack.
The quality of our signals directly determines how well every downstream ML model performs: better signals mean better targeting, higher CTR/CVR, and stronger monetization. We own the full lifecycle — from raw event ingestion and large-scale feature pipelines, to identity-prediction models, embeddings, and online serving — and we close the loop by applying those outputs inside the ads models that consume them in real time.
About the role
We are looking for an experienced Senior Machine Learning Engineer to design and build the data and ML systems that transform raw user signals into production targeting and bidding features. This is a hands-on, high-ownership role that blends ML modeling, large-scale data engineering, and production ML systems.
You will own significant pieces of the signal-to-model pipeline end to end: defining and building features at scale, developing models for user understanding — most importantly identity prediction — and then applying those predictions directly inside the ads targeting, bidding, and ranking models to drive measurable lift. You won't just hand features off to a downstream team; you'll close the loop, ensuring everything is served online with the freshness, latency, and reliability that real-time bidding demands. You'll partner closely with Ads, Data, and Infra teams, and you'll be expected to drive technical direction — not just execute well-scoped tasks.
Responsibilities
- Build user-signal features at scale: design, implement, and own offline and online feature pipelines (batch + streaming) that turn raw user events into high-quality targeting and bidding features.
- Develop user-understanding models — especially identity prediction: build and improve models such as identity prediction, user/content embeddings, intent and conversion prediction, and signal-quality / value models that feed ads targeting and bidding.
- Apply model outputs inside ads models: integrate identity-prediction results and other user signals directly into the ads targeting, bidding, and ranking models — owning the impact all the way to revenue, not just the upstream features.
- Own the model lifecycle: data preparation, feature engineering, training, offline/online evaluation, deployment, monitoring, and iteration — with rigorous A/B testing and clear business metrics (CTR, CVR, ROAS, revenue).
- Bridge modeling and serving: ensure features and model outputs are available online with the freshness and low latency required by high-QPS real-time bidding, working across feature stores, embedding stores, and serving infra.
- Improve signal quality and coverage: identify gaps, biases, and freshness issues in user signals; build the data quality, labeling, and validation systems that keep features trustworthy.
- Collaborate cross-functionally with Ads ranking/bidding, Data, and Platform teams to align signal and feature design with downstream model and business needs.
- Provide technical leadership: drive design reviews, set best practices for ML and feature engineering, mentor engineers, and raise the quality bar for the team.
Requirements
- Bachelor's or Master's degree in Computer Science, Machine Learning, Statistics, or a related quantitative field (or equivalent practical experience).
- 5+ years of industry experience as an ML engineer / applied scientist, building and shipping ML models in production (not just research or offline prototyping).
- Strong foundation in machine learning: feature engineering, supervised learning, embeddings/representation learning, and offline + online evaluation methodology.
- Proficiency in Python and a solid ML stack (e.g. PyTorch or TensorFlow, scikit-learn, pandas/NumPy).
- Hands-on experience with large-scale data processing for ML — e.g. Spark, Flink, SQL/Presto/Trino — including building production feature or training-data pipelines.
- Experience taking models from idea to production: training, deployment, monitoring, and iterating based on real metrics and A/B tests.
- Strong analytical and problem-solving skills, and the ability to reason about model behavior, data quality, and business impact end to end.
Preferred Qualifications
- Direct experience in Ads, recommendation, search, or growth ML — especially targeting, bidding, ranking, CTR/CVR prediction, or identity prediction.
- Experience with user-signal / behavioral data: event pipelines, identity prediction, user embeddings, and applying model outputs back into downstream ranking/bidding models.
- Familiarity with online feature serving — feature stores, embedding/vector stores, and low-latency, high-QPS inference for real-time bidding.
- Experience with streaming systems (Kafka, Flink, Spark Streaming) for real-time feature computation.
- Knowledge of the big-data ecosystem (Hadoop, Spark, Hive, Presto/Trino) and modern ML platforms / MLOps tooling (training orchestration, experiment tracking, model registries, feature stores).
- Experience with large-scale / distributed model training and inference optimization (e.g. distributed training, embedding tables, quantization, efficient serving).
- A track record of measurable business impact (revenue, ROAS, CTR/CVR lift) from ML work, and of driving technical direction across teams.
What we offer
- The chance to own a mission-critical part of the ads stack — the user signals and features that every targeting and bidding model depends on.
- Real end-to-end ownership: from raw signal to production model to measurable revenue impact, with high visibility across Ads and business leadership.
- Collaboration with strong Ads, ML, and Data engineers on internet-scale problems.
- Competitive compensation and benefits.
Benefits
We offer a competitive benefits package:
- Health, dental, and vision care for you and your family (100% coverage for employee)
- Top-tier 401(K) plan with company matching
- Paid time off and paid holidays
- FSA, HSA and commuter benefits programs
- Team activity budget
The US base salary range for this full-time position is listed below. Pay may vary based on a number of factors including job-related skills, level, experience, geographic location and relevant education or training. At NewsBreak, we design our overall rewards package to attract top talents. Depending on the position, the role may also be eligible for discretionary bonus and options. Your recruiter can share more details during the hiring process.
Annual Base Pay Range
$185,000—$235,000 USD
CPRA Privacy Notice for California Candidates
