Reach out directly about this role
Hello! This is GigaChat Reasoning — the team that gives the model the superpower to reason. We create environments, train via online RL, accelerate learning, and bring solutions to production.
Directions
Improving GigaChat Reasoning: full training cycle from cold start to deploying the model to production. Adding new domains, creating datasets, and answer evaluation functions.
Developing agent skills and tool calling using Online RL: creating training environments for LLMs, training and testing models.
Improving the Deep Research product
For these roles, we are looking for a talented NLP Engineer with knowledge and experience in Reinforcement Learning. For all these experiments, we have a cluster with a large number of A/H 100s.
Remote within Russia.
Possibility of employment in an IT-accredited company
Annual performance bonus up to 6 months' salary.
Regular salary reviews.
Corporate gym and relaxation areas.
More than 400 programs of SberUniversity for growth.
Onboarding program and manager's support at the start.
Largest DS&AI community – over 600 DS from the bank, regular exchange of knowledge, experience and best practices, interactive lectures and master classes from leading universities and experts from technology companies, digest of the latest developments in DS&AI and reports from the world's largest conferences, regular internal meetups.
Extended health insurance, preferential family insurance, corporate pension program.
Employee mortgage under a discount program.
SberPrime+ and discounts with partners.
Referral bonus for recommendations to the team
3-6 years
Experience
Full-time
Employment
Onsite
Work Format
Senior
Grade
Data Science & ML
Specialization
AI
Industry
Corporation
Company Type
By city
Data Science & ML
Specialization
AI
Industry
Corporation
Company Type