About the job
This role is part of Uber’s ML Serving team within the AI Platform, responsible for building and operating large-scale, low-latency systems for real-time ML and generative AI inference. As a Senior Software Engineer, you will lead the design and ownership of critical serving services and frameworks that power ML workloads across Uber. Your work will directly influence platform reliability, scalability, and developer experience for ML engineers company-wide.
Responsibilities
Design, build, and own scalable ML serving services and infrastructure components
Drive technical design decisions and lead the implementation of complex systems
Partner with ML engineers and platform teams to productionize ML and generative AI models
Improve system reliability, performance, and operational excellence through automation and tooling
Mentor junior engineers and contribute to team-wide engineering best practices
Qualifications
Minimum
5+ years of experience in Software Engineering
Significant experience building production-grade backend or distributed systems using Java, Go, Python, or C++
Proven ability to design, ship, and operate scalable services end to end
Strong foundation in system design, data structures, and algorithms
Hands-on experience with ML serving, inference pipelines, or real-time ML systems in production
Preferred
Experience designing high-throughput, low-latency distributed systems
Familiarity with ML frameworks and model lifecycle concepts such as deployment, versioning, and monitoring
Demonstrated ownership, mentoring, and collaboration across teams