Staff Software Engineer - Engineer
Staff Software Engineer focused on building and scaling ML inference infrastructure at Uber, optimizing ML models for production environments, and collaborating with research and product teams.
What you'd actually do
- Build and scale ML inference infrastructure to serve millions of users.
- Optimize ML models for production performance, latency, and cost.
- Collaborate with ML researchers and product teams to deploy and integrate ML models.
- Develop and maintain tools and frameworks for ML model deployment and monitoring.
- Contribute to the overall ML platform strategy and roadmap.
Skills
Required
- Proficiency in Python and C++
- Experience with ML frameworks (e.g., TensorFlow, PyTorch)
- Deep understanding of ML inference and serving technologies
- Experience with cloud platforms (AWS, GCP, Azure)
- Strong software engineering fundamentals
Nice to have
- Experience with distributed systems
- Familiarity with MLOps tools and practices
- Experience with GPU optimization
What the JD emphasized
- scale ML inference infrastructure
- optimize ML models for production
- deploy and integrate ML models
Other signals
- Build and scale ML inference infrastructure
- Optimize ML models for production
- Collaborate with ML researchers and product teams