Team Lead for ML Platform Development

About the Company and Team

We are launching a large-scale project that will make the lives of our colleagues more convenient. The users of the new service will be hundreds of Yandex ML developer teams, who train models for Alice, Neuro, Shedevrum, and other products.

The service will include several key components: Managed DevCluster for remote development and test runs on GPUs; a tool for simple and effective launching of training processes on the YTsaurus cluster with thousands of GPUs; an orchestrator that will allow describing data preparation graphs in Python and SQL; a solution for tracking ML experiments (similar to Weights & Biases); an MLOps system for storing models and managing their lifecycle.

We are looking for an experienced Team Lead who understands the development of complex, high-load systems. You will manage a small team, oversee cross-team projects, and write code for the services of Yandex's future ML platform.

What Tasks Await You

Team Management You will lead a team of two developers: assign tasks, conduct code reviews, control deadlines, care about the professional development and satisfaction of colleagues, fairly distribute tasks, and recognize employee achievements.

Cross-Team Project Management Creating a global ML infrastructure affects many adjacent departments. You will be the connecting link: synchronize with base infrastructure teams and ML developers, plan releases, and manage the implementation of new solutions.

Creating a Cluster for Remote Development You will create a solution that allows developers to share powerful machines with GPUs for debugging code without mutual interference.

We Expect You To Have

• Developed complex systems in Go, C++, or Java (experience with one language is sufficient, but the work will be in Go)
• Led a team of developers (mentorship, performance review, task distribution) or are ready for this role
• Manage cross-team projects, gather requirements, and negotiate with stakeholders
• Write quality code with an eye on the given service architecture
• Understand the principles of developing high-load applications
• Understand how containerization works in Linux
• Be ready to delve into the specifics of ML model work at Yandex and implement new infrastructure solutions

It Will Be a Plus If You Have

• Participated in the creation and implementation of infrastructure solutions in large companies
• Are familiar with infrastructure systems (Docker, Kubernetes, Ray, Slurm) or MLOps tools

What We Offer:

• Extended Medical Insurance starts working from the first month at Yandex. It includes dentistry, annual check-ups, emergency assistance abroad, treatment for critical illnesses, including oncology, and accident insurance.

As well as:

• psychotherapy in the office or online services;
• laser vision correction after a year of work;
• pregnancy management and childbirth - after two years.

Insurance for relatives under the 80/20 system. We pay 80% of the cost of voluntary medical insurance for children and spouses, you pay the remaining 20%.

• Development and Growth

Yandex has everything to continuously develop and learn new things: an internal educational platform, mentorship, and programs for junior and experienced managers.

We also cover participation in industry conferences - both as a speaker and as an attendee.

In addition, Yandex has internal projects where our employees share expertise, discuss complex topics, and analyze their project cases.

• Flexible Schedule

We do not have fixed start and end times for the workday - work in a way that is convenient for you and your team.

• Housing Loans

Preferential rates for purchasing housing and improving living conditions - depending on tenure, position, and review results. Valid for employees working in Yandex's Russian offices.

• Everything for Children

Insurance, children's days in the office, gifts for the birth of children, and check-ups when planning a pregnancy.