Senior Software Engineer, Forecasting & Real-Time Optimization

Lyft • San Francisco, CA

4d • $148,000 - $185,000 • Hybrid

About The Position

The Senior Software Engineer will join Lyft’s Forecasting and Real-Time Optimization Platform (FORTOP) team in the Rideshare Experience & Marketplace organization. The team provides reliable, real-time marketplace supply and demand signals and forecasts that support automated business decisions and products such as Dynamic Pricing, Real-Time Supply Management, Fulfillment, and Driver Incentives.

The role leads the design and operation of production systems that turn streaming marketplace data into accurate, reliable forecasts. This includes real-time feature pipelines, model training and inference infrastructure, backtesting and evaluation tooling, and signal-serving systems used continuously by downstream products. The engineer partners with scientists to bring models from prototype to production and works with downstream teams to establish interfaces, data contracts, and reliability guarantees. Forecasts cover rider demand and driver supply as they change with traffic, holidays, and major events, with a focus on keeping systems correct and fast during peak periods.

This is a hybrid role requiring in-office work three days per week, on Mondays, Wednesdays, and Thursdays. Hybrid employees may work from anywhere for up to four weeks per year. The expected base pay range in the San Francisco area is $148,000–$185,000, excluding potential equity, bonus, and benefits.

Requirements

• At least 5 years of software engineering industry experience, including building and operating backend or data systems in production.
• BS/MS or equivalent in Computer Engineering, Computer Science, or a related field, or relevant work experience.
• Experience designing and leading delivery of large-scale distributed systems and owning their reliability through monitoring, on-call, and incident response.
• Solid distributed-systems fundamentals, including fault tolerance, delivery semantics, and consistency tradeoffs.
• Track record of leading ambiguous, multi-engineer projects and mentoring other engineers.
• Clear written communication, including design documents that align stakeholders.

Nice To Haves

• Experience building production machine-learning models and infrastructure, including model selection, feature engineering and pipelines, training and inference pipelines, model serving, or ML platforms.
• Hands-on experience with stream or large-scale batch processing such as Flink, Beam, or Spark, and distributed messaging such as Kafka or Kinesis.
• Experience with time-series forecasting systems, or familiarity with backtesting and forecast evaluation, including error metrics, bias, and calibration.
• Experience with online experimentation or real-time decision systems such as pricing, dispatch, or marketplace balancing.
• Comfort using AI-assisted development tools to move faster without compromising quality.

Responsibilities

• Lead multi-engineer projects from proposal and technical design through launch; set milestones, coordinate dependencies with partner teams, and own estimates.
• Design and evolve streaming feature pipelines, model training and inference workflows, and signal-serving systems, with attention to latency, correctness, scalability, and cost.
• Lead design reviews and reduce system complexity by consolidating or sunsetting components.
• Partner with scientists to design and productionize machine-learning models.
• Build rollout tooling, including shadow, canary, and rollback capabilities, as well as backtesting and experimentation infrastructure.
• Define and maintain interfaces, data contracts, and SLAs for forecasting signals used by downstream consumers such as Dynamic Pricing and Driver Incentives.
• Monitor system health and signal quality, prepare systems for peak events, participate in on-call, lead post-incident investigations, and complete follow-up actions.
• Write well-tested, maintainable code; review colleagues’ code; and coach teammates on testing and engineering practices.
• Collaborate with Product, Science, and partner engineering teams to frame problems, shape the roadmap, and make tradeoffs among accuracy, latency, and complexity.
• Mentor engineers, participate in hiring and onboarding, and share knowledge through design documents, runbooks, and technical talks.

Benefits

• Medical, dental, and vision insurance options, with additional programs available when enrolled.
• Mental health benefits.
• Family-building benefits.
• Child care and pet benefits.
• 401(k) plan with company match.
• 12 observed holidays; salaried team members receive discretionary paid time off, and hourly team members receive 15 days of paid time off.
• 18 weeks of paid parental leave for biological, adoptive, and foster parents.
• Subsidized commuter benefits.
• Monthly Lyft credits and complimentary Lyft Pink membership.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior