Description
AI CRO (Chief Risk Officer Agent) is a strategic AI agent, an intelligent assistant for executives and risk management specialists in a leading bank. Our agent understands natural language queries, plans action chains, calls dozens of internal risk services (provision calculation, credit ratings, stress tests) and returns business-justified answers, conclusions, and recommendations.
We are building the product from scratch on a modern stack: Python microservices, Kafka, REST, PostgreSQL, LLM integrations (GigaChat, LangChain/LangGraph frameworks).
The first stage of selection for this vacancy is a conversation with an AI recruiter. After you apply, you will receive an email invitation to take an initial interview with GigaRecruiter on Telegram. The dialogue will take approximately 10 minutes. Its goal is to clarify missing details and speed up the review of your application.
GigaRecruiter is just starting its journey, so we ask for your understanding. Your experience and participation will help make it convenient and useful!
Responsibilities
- designing the AI agent testing strategy
- writing Python autotests for regression testing of a test suite in CI/CD.
- integration testing of the agent's interaction with risk services (REST, Kafka), checking timeout handling, errors, idempotency.
- incident investigation: analyzing logs, traces, reproducing issues.
- preparing quality reports for the team and management
- integrating tests into pipelines, setting up quality monitoring (dashboards, alerts on metric drops).
- supporting isolated test environments (sandbox) for safe agent runs.
Requirements
- experience testing complex backend systems for 3+ years — testing microservices, integrations, asynchronous scenarios (Kafka, REST).
- test automation skills in Python (pytest, requests, working with JSON) — ability to write scripts for running scenarios and validating responses.
- understanding of REST API, experience with OpenAPI, writing API autotests
- experience testing integrations via message brokers (Kafka) — checking topics, keys, offsets, delivery guarantees, failure handling
- knowledge of SQL at the level of complex queries (joins, aggregations, window functions) for data verification in PostgreSQL
- experience in log analysis and incident investigation — working with ELK/Kibana, reading Python stack traces
- understanding of CI/CD and the role of testing in pipelines (Jenkins/GitLab CI), experience integrating autotests.
Conditions
- office near Kutuzovskaya metro station
- work format: hybrid
- annual salary review and annual bonus
- corporate gym and relaxation areas
- more than 400 educational programs from SberUniversity for professional and career development
- extended VHI (Voluntary Health Insurance), preferential insurance for family and corporate pension program
- flexible mortgage discount equal to 1/3 of the Central Bank key rate
- free SberPrime+ subscription, discounts on products from partner companies
- referral bonus for recommending friends to the Sber team.
