Engineering Manager (ML Serving)
Job Description
Anyscale is looking for a strong Engineering Manager to lead the ML Serving team. The ML Serving team’s charter is to make “Ray for production” a reality. This includes managing batch jobs, highly available services as well as driving the vision of the Ray Serve library – the fastest-growing open-source library for production ML serving – which is a serving layer built on top of Ray that's specifically targeted at building low-latency ML inference pipelines. This involves working closely with open source and Anyscale users to build the best API for defining ML serving applications, architecting and building on top of Ray for low latency and high scalability, and building out highly-available infrastructure in the Anyscale product for running batch jobs and highly available services.
In this position, you will guide the vision, recruit, and enable a high-performing engineering team that delivers critical values to developers in open source and Anyscale customers.
Responsibilities
- Drive the strategy of the fastest growing open-source library for production ML Serving
- Building out proprietary highly-available, scalable serving infrastructure in the Anyscale product
- Work with a team of leading distributed systems and machine learning experts
- Lead the team to deliver key software features as well as enhance the quality of the existing codebase
- Meet open source partners and Anyscale customers, representing engineering at these strategic discussions.
- Collaborate closely with the product design and product management teams to iterate and refine product requirements
- Work closely with other teams at the company, including proprietary product and open source engineering, marketing, sales, etc.
- Execute well in a high-impact environment
- Recruit new employees and coach/mentor engineers
- Design and implement scalable engineering processes.
- Focus on building and maintaining a culture of collaboration within the team.
- Communicate your work to a broader audience through talks, tutorials, and blog posts
- Help us to build and shape a world-class company
Job Requirements
- Experience building highly available serving systems
- Experience building and operating machine learning infrastructure in production
- Solid engineering management experience leading productive, high-performing teams.
- Record of helping teams scale quickly while maintaining a good culture
- Ability to ensure a high hiring bar, motivate team, coach/mentor, and handle performance management issues.
- Deep technical knowledge and experience in distributed systems or machine learning is a plus
- A great track record of execution
- A sense of urgency, a mindset towards achieving results, and excellent prioritization skills
- Effective communication
