Senior Backend Engineer - Real-Time ML Infrastructure

At Lyft, our purpose is to serve and connect. Marketplace teams sit at the very heart of Lyft’s products and decision-making, building predictive, personalized, and adaptive systems that empower riders and drivers to make the most effective use of our platform.

The Forecasting and Real-Time Optimization Platform (FORTOP) team inside Lyft’s Rideshare Experience & Marketplace (REM) organization provides real-time market supply and demand signals and forecasts that power critical automated decisions across the business. These signals feed core marketplace engines, including Dynamic Pricing, Real-Time Supply Management, Driver Incentives, and Fulfillment.

As a Senior Software Engineer on FORTOP’s forecasting team, you will lead the architecture and operations of production systems that transform streaming marketplace data into reliable forecasts. You will own streaming feature pipelines, model training and inference infrastructure, backtesting tools, and high-concurrency signal-serving layers. Partnering closely with Data Scientists and downstream engineering teams, you will scale systems that forecast rider demand and driver supply amid shifting traffic, holidays, and peak demand events.

Key Responsibilities

• End-to-End Technical Leadership: Lead multi-engineer projects from proposal and technical design through launch. Break down work into milestones, align partner team dependencies, and own technical deliverables.
• ML Systems Architecture: Design and evolve streaming feature pipelines, training/inference workflows, and signal-serving APIs. Conduct design reviews focused on latency, correctness, scalability, and cost efficiency.
• Production ML & Science Partnership: Partner with scientists to take models from prototype to production. Build rollout tooling (shadow, canary, automated rollback), backtesting engines, and online experimentation infrastructure.
• Signal Contracts & Interfaces: Define and maintain data contracts, interfaces, and SLAs between forecasting signals and downstream systems (Dynamic Pricing, Dispatch, Incentives).
• System Operations & On-Call: Monitor system health (latency, freshness, error rates) and signal quality (accuracy, bias, drift). Participate in on-call rotation, lead post-incident reviews, and drive remediation.
• Code Quality & Mentorship: Write maintainable, well-tested code, perform peer code reviews, mentor junior engineers, and contribute to engineering standards, runbooks, and tech talks.

Requirements

Distributed Systems & Backend Depth

• 5+ years of professional software engineering experience building and operating backend or data systems in production environments.
• Degree: Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related technical field (or equivalent practical experience).
• Distributed Systems Mastery: Demonstrated success designing, delivering, and operating large-scale distributed systems. Strong understanding of fault tolerance, delivery semantics, and consistency trade-offs.
• Technical Leadership: Track record of leading ambiguous, multi-engineer projects, authoring clear technical design documents, and aligning cross-functional stakeholders.

Preferred Qualifications

• Experience building production ML infrastructure, including feature stores, model training/inference pipelines, or ML platform tooling.
• Hands-on experience with streaming and large-scale batch processing (Apache Flink, Apache Beam, Apache Spark) and message streaming (Apache Kafka, AWS Kinesis).
• Experience with time series forecasting systems, backtesting frameworks, and evaluation metrics (error rates, bias, calibration).
• Background in online experimentation or real-time marketplace systems (dynamic pricing, dispatch, dispatch balancing).
• Comfort utilizing AI-assisted development tools to accelerate workflow productivity without sacrificing code quality.

Total Rewards & Benefits

• Compensation & Equity: Expected base salary of $148,000 – $185,000 USD (San Francisco) + equity grants + performance bonus eligibility.
• Healthcare & Mental Health: Medical, dental, and vision insurance options, plus dedicated mental health programs.
• Family & Caregiver Benefits: 18 weeks of paid parental leave (biological, adoptive, and foster parents), family building assistance, childcare, and pet benefits.
• Time Off & Flexibility: Discretionary paid time off (salaried) + 12 observed company holidays, plus 4 weeks per year to work remotely from anywhere.
• Lyft Perks & Commuter: Monthly Lyft credits, complimentary Lyft Pink membership, subsidized commuter benefits, and 401(k) company match.