About the Team
Come help us build the world's most reliable on-demand, logistics engine for delivery! We're bringing on talented data scientists to help us develop and improve the models that power DoorDash's three-sided marketplace of consumers, merchants, and dashers.
About the Role
DoorDash users use the DoorDash app in two modes: 1) to search for restaurants and products when they have something in mind; 2) to discover new dishes, restaurants, and products for delivery when they do not have something specific in mind. Both use cases are very important to our users. As a recommendation and search-focused Machine Learning Scientist you will have the opportunity to identify and prioritize machine learning investments to address both of these use cases. You will leverage our robust data and infrastructure to develop models that impact millions of users across our three audiences. You will partner with an engineering lead and product manager to set the strategy that moves the business metrics which help us grow our business.
You’re excited about this opportunity because you will…
- Lead the effort for query understanding: Applying active learning, semi-supervised learning, query embedding, product and merchant embedding, entity extraction and canonicalization to improve understanding of the consumer’s intent as expressed by search query
- Drive the personalization for search and recommendation: Building models to understand user’s preferences for merchant segments, product categories, dish categories, dietary preferences, etc., furthermore the personalization based on these learned preferences, and addressing the potentially significant cold start problem
- Extend the search and recommendation platform from the merchant level to the item level: At the item level, the candidate set is billions in size instead of millions at the merchant level. This 1,000x increase in candidate set makes the problem much more challenging and exciting
- You can find out more on our ML blog post here
We’re excited about you because…
- High-energy and confident — you keep the mission in mind, take ideas and help them grow using data and rigorous testing, show evidence of progress and then double down
- You’re an owner — driven, focused, and quick to take ownership of your work
- Humble — you’re willing to jump in and you’re open to feedback
- Adaptable, resilient, and able to thrive in ambiguity — things change quickly in our fast-paced startup and you’ll need to be able to keep up!
- Growth-minded — you’re eager to expand your skill set and excited to carve out your career path in a hyper-growth setting
- Desire for impact — ready to take on a lot of responsibility and work collaboratively with your team
- 4+ years of industry experience developing recommendation/search models with business impact — more experience preferred
- 1+ years of industry experience serving in a tech lead role
- M.S., or PhD. in Statistics, Computer Science, Electric Engineering, Math, Operations Research, Physics, Economics, or other quantitative field
- Prior experience with query understanding a plus
- Good working knowledge of embedding based methods, deep learning models, and graph based models preferred
- Demonstrated familiarity with programming languages e.g. python and machine learning libraries e.g. SciKit Learn, Spark MLLib
- Experience productionizing and A/B testing different machine learning models
At DoorDash, our mission to empower local economies shapes how our team members move quickly, learn, and reiterate in order to make impactful decisions that display empathy for our range of users—from Dashers to merchant partners to consumers. We are a technology and logistics company that started with door-to-door delivery, and we are looking for team members who can help us go from a company that is known for delivering food to a company that people turn to for any and all goods.
DoorDash is growing rapidly and changing constantly, which gives our team members the opportunity to share their unique perspectives, solve new challenges, and own their careers. We're committed to supporting employees’ happiness, healthiness, and overall well-being by providing comprehensive benefits and perks including premium healthcare, wellness expense reimbursement, paid parental leave and more.
Our Commitment to Diversity and Inclusion
We’re committed to growing and empowering a more inclusive community within our company, industry, and cities. That’s why we hire and cultivate diverse teams of people from all backgrounds, experiences, and perspectives. We believe that true innovation happens when everyone has room at the table and the tools, resources, and opportunity to excel.
Statement of Non-Discrimination: In keeping with our beliefs and goals, no employee or applicant will face discrimination or harassment based on: race, color, ancestry, national origin, religion, age, gender, marital/domestic partner status, sexual orientation, gender identity or expression, disability status, or veteran status. Above and beyond discrimination and harassment based on “protected categories,” we also strive to prevent other subtler forms of inappropriate behavior (i.e., stereotyping) from ever gaining a foothold in our office. Whether blatant or hidden, barriers to success have no place at DoorDash. We value a diverse workforce – people who identify as women, non-binary or gender non-conforming, LGBTQIA+, American Indian or Native Alaskan, Black or African American, Hispanic or Latinx, Native Hawaiian or Other Pacific Islander, differently-abled, caretakers and parents, and veterans are strongly encouraged to apply. Thank you to the Level Playing Field Institute for this statement of non-discrimination.
Pursuant to the San Francisco Fair Chance Ordinance, Los Angeles Fair Chance Initiative for Hiring Ordinance, and any other state or local hiring regulations, we will consider for employment any qualified applicant, including those with arrest and conviction records, in a manner consistent with the applicable regulation.
If you need any accommodations, please inform your recruiting contact upon initial connection.