Product Manager, Forecasting
At Lyft, we're developing a wide range of forecasting models that help Lyft deliver better products and make sure the experience to both the driver and the passenger is optimal.
We are looking for a rockstar PM who can lead our forecasting platform efforts - from tools needed for internal modeling optimization, through setting goals and managing the process of developing various ML models for Forecasting, to the creation of interfaces for other Lyft product teams to consume Forecasting output.
The quality and reliability of our Forecasting platform models and tools directly contribute to Lyft's ability to deliver the best experience to passengers and drivers and to optimize internal processes and resource use.
The Forecasting team relies on Big Data and ML platform tools developed internally to access and process data both in real-time and in offline modes and link features and models into complete Machine Learning pipelines that would be used in a variety of production scenarios.
Responsibilities:
- Design and manage the process of building forecasting platform tools that would simplify forecasting model development and delivery to customer teams across Lyft
- Prioritize ML modeling work covering the span of forecasting problems Lyft faces and work with ML model developers to ensure optimal delivery of developed models
- Define the interfaces through which forecasts are delivered to customers and ensure we have the right systems and tools to deliver our forecasts via these interfaces
- Work with customer teams to ensure they use our Forecasting services in the optimal way and collect feedback to improve our Forecasting services metrics (e.g. accuracy, prediction interval) and performance (e.g. latency and output structure)
- Have a strong technical background with experience in designing Machine Learning tools and algorithms
- Keep track of activities in the external ML community so we'd quickly identify opportunities and around Forecasting models, tools and techniques
Experience & Skills:
- Detail oriented with superior organizational skills
- Minimum of 4 years of relevant product management or data science experience
- An academic background in an engineering or quantitative discipline
- Strong analytical capability
- Strong business acumen
- Natural ability to make things happen around you
- Strong communication skills
- Familiarity with ML modeling workflows and basics of Data Science: feature selection and engineering, different ML model families, optimization considerations for ML models, deployment and serving challenges
- Familiarity with ML algorithms = linear/logistic regression, random forest, gradient boosted trees, Deep Learning
- Familiarity with service-oriented architecture and systems design (since forecasting model output will be delivered as services/APIs to other teams)
Nice to Have:
- Familiarity with ML platforms = TensorFlow, PyTorch, SKLearn
- Knowledge of big data systems = Spark, Hadoop, Kubernetes
- Past experience in designing/building forecasting models and tools
- Developed ML models on their own
- Keep track of recent academic papers
- Served previously in a Data Science or ML Engineer role
- Have an advanced degree in Machine Learning
Lyft is an Equal Employment Opportunity employer that proudly pursues and hires a diverse workforce. Lyft does not make hiring or employment decisions on the basis of race, color, religion or religious belief, ethnic or national origin, nationality, sex, gender, gender-identity, sexual orientation, disability, age, military or veteran status, or any other basis protected by applicable local, state, or federal laws or prohibited by Company policy. Lyft also strives for a healthy and safe workplace and strictly prohibits harassment of any kind. Pursuant to the San Francisco Fair Chance Ordinance and other similar state laws and local ordinances, and its internal policy, Lyft will also consider for employment qualified applicants with arrest and conviction records