Data Scientist, Optimization - Real-Time Supply Management

Socotra, Inc.; Toronto; Hybrid; CAD 108,000 - 135,000; Full time

Benefits offered by this job

Health coverage

Mental health

Family benefits

Child care

Health Savings Account

RRSP match

Flexible PTO

Parental leave

Commuter benefits

Job summary

Lyft is seeking a Data Scientist specializing in Algorithms to partner with product, engineering, and operations to design and scale driver incentive systems. You will shape mechanism design strategy and deliver on marketplace efficiency and earnings goals in a fast-paced environment.

Ideal candidates have strong optimization, causal inference, or ML backgrounds, and hands-on experience with Python. Hybrid in-office role requires collaboration and data-driven decision making.

Qualifications

• Advanced degree in a quantitative field; 2+ years in optimization/causal inference or machine learning.
• Strong optimization background; ML or causal inference welcome.
• End-to-end data experience: querying, aggregation, analysis, and visualization.
• Proficiency with Python.
• Strong collaboration and communication in a team setting.
• Experience designing, running, and analyzing A/B tests.

Responsibilities

• Collaborate with engineering and product teams to design, implement, and iterate on new features and algorithmic improvements for driver incentives and pay mechanisms.
• Design, develop, and deploy optimization models, algorithms, and systems for budget allocation, multidimensional cost‑curve development, and incentive targeting.
• Write production model code; collaborate with Software Engineers to implement algorithms in production.
• Perform exploratory data analysis to gain a deeper understanding of the marketplace and its users.
• Communicate findings and facilitate launch decisions with technical and non-technical stakeholders.
• Ensure robust experimentation and causal inference methodologies are applied to measure the impact of new features and strategies.

Skills

Optimization

Python

A/B testing

Data analysis

Communication

Team collaboration

Machine learning

Education

MS/PhD in quantitative field

Job description

At Lyft, our purpose is to serve and connect. We aim to achieve this by cultivating a work environment where all team members belong and have the opportunity to thrive.

Data Science is at the heart of Lyft’s products and decision-making. Data Scientists at Lyft operate in dynamic environments, moving quickly to build the world’s best transportation solutions. We tackle a wide range of challenges - from shaping long-term business strategy with data, to making critical short-term decisions, to developing algorithms and models that power both internal systems and customer-facing products.

Driver Incentives Science owns the algorithms and systems behind incentive design, influencing driver engagement and marketplace efficiency — from real-time supply positioning to longer-horizon earnings and engagement programs. The team is responsible for designing pay and incentive mechanisms that are efficient and good for driver experience over the long run.

As a Data Scientist specializing in Algorithms, you'll partner closely with product, engineering, and operations leaders to build and scale incentive systems, shape long-term mechanism design strategy, and deliver on critical business goals tied to marketplace efficiency and driver earnings. Candidates with strong optimization backgrounds — think mathematical programming, control theory, or operations research — are a great fit, though we welcome strong candidates from machine learning or causal inference as well. The ideal candidate thrives in a fast-paced environment and brings a hands‑on, entrepreneurial mindset to drive results.

Responsibilities:

• Collaborate with engineering and product teams to design, implement, and iterate on new features and algorithmic improvements for driver incentives and pay mechanisms.
• Design, develop, and deploy optimization models, algorithms, and systems for problems such as budget allocation, multidimensional cost‑curve development, and incentive targeting.
• Write production model code; collaborate with Software Engineers to implement algorithms in production.
• Perform exploratory data analysis to gain a deeper understanding of the marketplace and its users.
• Communicate findings and facilitate launch decisions with technical and non-technical stakeholders.
• Ensure robust experimentation and causal inference methodologies are applied to measure the impact of new features and strategies.

Experience:

• Advanced degree (MS or PhD, PhD preferred) in a quantitative field like Operations Research, Applied Math, Computer Science, Statistics, Engineering, or a related area; or equivalent work experience.
• Passion for solving unstructured and non‑standard mathematical problems, with 2+ years of hands‑on experience in optimization (preferred), causal inference, or machine learning.
• End‑to‑end experience with data, including querying, aggregation, analysis, and visualization.
• Proficiency with Python.
• Strong ability to collaborate and communicate with others in a team setting.
• Experience seeking out and adopting new methods and techniques.
• Experience designing, running, and analyzing A/B tests to validate hypotheses and inform decision‑making.

Benefits:

• Extended health and dental coverage options, along with life insurance and disability benefits
• Mental health benefits
• Family building benefits
• Child care and pet benefits
• Access to a Lyft funded Health Care Savings Account
• RRSP plan with company match to help save for your future
• In addition to provincial observed holidays, salaried team members are covered under Lyft's flexible paid time off policy. The policy allows team members to take off as much time as they need (with manager approval). Hourly team members get 15 days paid time off, with an additional day for each year of service
• Lyft is proud to support new parents with 18 weeks of paid time off, designed as a top‑up plan to complement provincial programs. Biological, adoptive, and foster parents are all eligible.
• Subsidized commuter benefits and Lyft ride credits

Lyft is committed to creating an inclusive workforce that fosters belonging. Lyft believes that every person has a right to equal employment opportunities without discrimination because of race, ancestry, place of origin, colour, ethnic origin, citizenship, creed, sex, sexual orientation, gender identity, gender expression, age, marital status, family status, disability, pardoned record of offences, or any other basis protected by applicable law or by Company policy. Lyft also strives for a healthy and safe workplace and strictly prohibits harassment of any kind. Accommodation for persons with disabilities will be provided upon request in accordance with applicable law during the application and hiring process. Please contact your recruiter if you wish to make such a request.

Lyft highly values having employees working in‑office to foster a collaborative work environment and company culture. This role will be in‑office on a hybrid schedule — Team Members will be expected to work in the office at least 3 days per week, including on Mondays, Wednesdays, and Thursdays. Lyft considers working in the office at least 3 days per week to be an essential function of this hybrid role. Your recruiter can share more information about the various in‑office perks Lyft offers. Additionally, hybrid roles have the flexibility to work from anywhere for up to 4 weeks per year. #Hybrid

The expected base pay range for this position in the Toronto area is CAD $108,000 - CAD $135,000, not inclusive of potential equity offering, bonus or benefits. Salary ranges are dependent on a variety of factors, including qualifications, experience and geographic location. Your recruiter can share more information about the salary range specific to your working location and other factors during the hiring process.

Lyft may use artificial intelligence to screen applicants, however, Lyft employees make the ultimate selection and hiring decisions.

This job fills an existing vacancy.