高级数据科学家,留存与产品
Senior Data Scientist, Retention & Product
关于CookUnity:
食物在现代便利中失去了灵魂。随之而来的,是它失去了滋养、启发和连接我们的力量。因此,2018年,CookUnity作为首个此类平台成立,将世界与真正美味食物的源头:厨师们联系在一起。如今,CookUnity每年从业内最佳厨师那里为全国各地的家庭提供5000万份餐食。新鲜、即食,并以滋养身心的热情精心制作。
我们不愿止步于此,CookUnity正在扩大业务范围,超越配送,成为不断创新的市场,专注于我们的单一使命:赋能厨师,滋养世界。
如果这个使命让你在更多方面感到兴奋,那么你找到了正确的职位公告。
职位描述:
我们正在招聘一名以机器学习为重点的数据科学家,负责CookUnity的留存和流失问题。在每周订阅业务中,留存是增长的引擎——健康客户和流失客户之间的差距往往只是几周的活动。你的工作是预测谁有风险,了解他们离开的原因,并推动能够留住客户并挽回流失客户的干预措施。这是一个与产品、CRM、营销和工程团队紧密合作的实操岗位。
职责:
- 流失与留存建模:构建流失/生存模型和生命周期状态模型,尽早标记有风险的客户,并预测每个客户的发展方向。
- 干预与原因理解:推动针对该风险的留存干预措施——保存流程、跳过/暂停规避、生命周期消息——并分类客户流失的原因,使响应与原因相匹配,而不是泛泛而谈。
- 挽救与挽回:开发倾向模型和个性化体验,将流失客户重新吸引回来。
- 个性化与下一步行动:根据客户情况,在产品各处决定正确的动作、优惠和信息,并通过提升层衡量增量影响。
- 优惠与促销优化:确定谁获得激励、何时获得以及价值多少——在不过度折扣的情况下最大化留存收入。
- 生产与MLOps:负责整个模型生命周期,并将模型部署到实际运行的系统中;处理监控、重新训练和漂移问题。
- 实验与增量性:设计实验和提升度测量,以便干预可移动的客户,而不是那些本来就会留存的客户。
任职要求:
- 5-8年以上数据科学、应用机器学习或统计学经验,有生产模型交付经验。
- 留存
查看英文原文
About CookUnity:
Food has lost its soul to modern convenience. And with it, it has lost the power to nourish, inspire, and connect us. So in 2018, CookUnity was founded as the first-of-its-kind platform that connects the world with the source of truly great food: chefs. Today, CookUnity delivers 50 million meals a year from the industry’s best chefs to homes all over the country. Fresh. Ready-to-eat. And crafted with the passion that nourishes body and soul.
Unwilling to stop there, CookUnity is expanding beyond delivery to become an ever-innovating marketplace focused on our singular mission: empower Chefs to nourish the world.
If that mission has you hungry in more ways than one, you’ve found the right job posting.
The role:
We're hiring an ML-focused Data Scientist to own retention and churn for CookUnity. In a weekly subscription business, retention is the engine of growth — the gap between a healthy customer and a churned one is often just a few weeks of activity. Your job is to predict who's at risk, understand why they leave, and power the interventions that keep customers ordering and win back the ones who go. This is a hands-on role embedded with Product, CRM, Marketing, and Engineering.
Responsibilities:
- Churn & retention modeling: Build churn/survival models and lifecycle-state models that flag at-risk customers early and anticipate where each customer is heading.
- Intervention & reason understanding: Power the retention interventions that act on that risk — save flows, skip/pause deflection, lifecycle messaging — and classify why customers churn so the response fits the reason rather than being generic.
- Resurrection & win-back: Develop propensity models and personalized experiences that bring churned customers back.
- Personalization & Next-Best-Action: Decide the right action, offer, and message per customer across product surfaces, with an uplift layer measuring incremental impact.
- Offer & promo optimization: Determine who gets an incentive, when, and at what value — maximizing retained revenue without over-discounting.
- Production & MLOps: Own the full model lifecycle and ship models into the systems where they act; handle monitoring, retraining, and drift.
- Experimentation & incrementality: Design experiments and uplift measurement so we intervene on movable customers and not on those who'd retain anyway.
Qualifications:
- 5-8+ years in data science, applied ML, or statistics, shipping production models.
- Retention/churn depth: churn prediction, survival / time-to-event modeling, and lifecycle-state models in a subscription or recurring-revenue context.
- Causal & experimentation rigor: uplift/incrementality measurement and A/B testing, with the judgment to separate true impact from selection effects.
- End-to-end ML & MLOps: building, validating, and deploying models in production (CI/CD, registries, containerization, orchestration, monitoring).
- Engineering & tooling: strong Python (pandas, scikit-learn, gradient boosting; deep learning a plus), SQL, code hygiene and reproducibility.
- Collaboration: excellent communication; able to embed with Product/CRM/Marketing and turn models into decisions.
- Education: BS in a quantitative field required; MS/PhD preferred.
- Ability to leverage generative AI to increase output quality and speed.
Preferred requirements:
- Subscription marketplaces, food-tech, or consumer marketplaces with a retention mandate.
- Lifecycle-state / Hidden Markov models for churn.
- Causal and uplift libraries (e.g. EconML) or survival-modeling packages.
- Recommenders, embeddings, or personalization for retention and win-back.
Learn More About CookUnity
We believe great leadership starts with alignment on vision, values, and ways of working. To give you deeper insight into who we are and what we’re looking for, we invite you to explore: CookUnity's Leadership Principles – The values and behaviors that guide how we operate, collaborate, and scale.
We hope this provides valuable insight into our culture and product vision. If this excites you, we’d love to connect!
Benefits
🩺 Health Insurance coverage
🌅 401k Plan
⛱ Unlimited PTO
🗓️ 5- year Sabbatical: After 5 years with CookUnity, you get a 4-week paid sabbatical
🐣 Paid Family leave
🕯 Compassionate Leave: 3-5 days each time the need arises
🥘 A generous amount of CookUnity credits to enjoy our amazing meals, added to your account, monthly
🤖 AI-forward workplace: enterprise access to ChatGPT and Claude to help you work smarter and grow faster.
🧘🏽♀️ Wellness perks: access to fitness subsidies to build a healthy lifestyle
👩🏾🏫 Personalized Spanish coach
🚀 Awesome opportunity to join a company that is looking to change how we eat and how chefs work!
Compensation
All final pay rates will be determined by candidates experience, knowledge, skills, and abilities of the applicant, internal equity, and alignment with market data.
Pay Range for this position
$160,000—$195,000 USD
If you’re interested in this role, please submit your application, and if we think you might be a fit, we'll get in touch with you. Thank you for your time!
CookUnity is an Equal Opportunity Employer. We are dedicated to creating a community of inclusion and an environment free from discrimination or harassment. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, age, sexual orientation, gender identity, national origin, citizenship status, protected veteran status, genetic information, or physical or mental disability.
A quick note for all candidates
We’ve recently seen an increase in recruitment scams across the industry, and we want to make sure you (and your data) stay safe while applying to CookUnity. We also want you to know that we take this seriously — sometimes, as part of our process, we may ask for a brief “proof of humanity” to confirm that we’re connecting with a real person, not an impersonator. Here are a few tips to help you protect yourself and know what to expect from us:
- Apply only through our official channels. All open roles are listed on our official careers page: careers.cookunity.com
- Our recruiters are real people — and easy to verify. You can always find them on LinkedIn with verified profiles. If you’re unsure, feel free to reach out to us on our official LinkedIn Company Page.
- We only communicate through official CookUnity channels. That means emails ending in @cookunity.com and interviews held through official company platforms (Google Meet or Zoom) — never WhatsApp, Telegram, or SMS.
- We’ll never ask for payment or personal financial details. If anyone does, please don’t share any information and let us know right away.
If something ever feels off or you’re unsure about a message, we’d much rather you double-check with us. You can always contact us directly through any of our social media channels. We appreciate your interest in joining CookUnity — and we care about keeping your experience (and safety) as genuine as possible.