Description
We are developing an ecosystem of AI assistants at Sber. Our product helps developers and analysts find answers to work-related questions faster, work with internal documentation and knowledge bases. We are not just building a "search engine", we are creating a smart assistant that saves team hours. Currently, we are actively scaling the system: teaching the assistant to solve more complex, multi-step tasks (agentic scenarios) and opening its capabilities to other services via API. We are looking for a business analyst who will help make our assistant even smarter and more useful for users
Who we are looking for:
- an analyst with 2+ years of experience, who is interested in working with products at the intersection of logic, data, and AI
- a person who knows how to communicate with different teams: from developers to data owners
- someone who doesn't just write requirements, but delves into user pain points and seeks the best ways to solve them.
Responsibilities
What you will be doing:
Increasing the assistant's usefulness:
- research what knowledge the assistant lacks for answers, and initiate the connection of new sources (internal knowledge bases, wikis, documents)
- monitor the quality of this data: whether it is up-to-date, complete, whether it helps the assistant give correct answers. Negotiate with data-owner teams to maintain quality
- analyze why the assistant answers inaccurately or cannot find information, and propose solutions on how to fix it (in terms of data and search logic).
Designing AI interaction scenarios:
- think through the assistant's logic: from simple answers to frequent questions to complex dialogues where the assistant can itself reach out to an external service (API) or clarify details with the user
- help the team configure the "personality" and usefulness of responses: participate in formulating prompts so that answers are accurate, safe, and comply with company policies
- describe how other teams and services will be able to use our assistant's capabilities via API.
Managing requirements and communications:
- transform user and business needs into clear tasks for the development team (user stories)
- be the link with other teams: agree on data exchange formats, synchronize integration plans
- maintain product documentation and backlog so that the entire team has a unified understanding of goals.
Requirements
Our expectations:
- ability to design user scenarios (experience with chat interfaces would be a big plus)
- understanding of how integrations (APIs) work, so you can set clear tasks for developers
- experience working with requirements and documentation (user stories, acceptance criteria)
- database skills (e.g., PostgreSQL) at the level of writing simple queries to test hypotheses
- critical thinking and proactivity: you don't need to wait for instructions to see what can be improved
- it would be great if you have already tried writing prompts and testing hypotheses, but this is not a strict requirement.
Conditions
Conditions:
- office in the "Danilovsky Fort" business center (Nagatinskaya metro station, Tulskaya metro station)
- 5/2 work schedule, hybrid work format possible
- no strict dress code
- VHI (voluntary health insurance) from the first day of work for employees and preferential medical insurance for close relatives
- corporate pension program
- corporate training at company expense
- employee referral program: you can invite professional acquaintances to the team and receive a reward of up to 100 thousand rubles
- corporate gym
- discounts on Sber products and ecosystem company products.
