Job
Description
:
Job TitleProduction Stability of AI Chatbot Application, AVP
LocationPune, India
Role Description
The AI chatbot application, designed to assist customers with bank-related queries, is a high-profile, mission-critical system with significant reputational impact. It directly supports customer experience and operational efficiency.The AI chatbot application plays a pivotal role in enhancing customer experience and reducing operational costs by providing 24/7 assistance for banking queries. Ensuring its stability in production is crucial.Given the high stakes of the AI chatbot application, hiring additional team members is essential to mitigate operational risks, maintain production stability, and protect the organizations reputation.These roles will provide the necessary redundancy, scalability, and incident-handling capabilities to ensure the application meets its service-level commitments and delivers a seamless customer experience. Currently, the team is understaffed, and with only one member managing production, the system is at risk of extended downtimes and delays in addressing high-priority incidents.
What well offer you
100% reimbursement under childcare assistance benefit (gender neutral)Sponsorship for Industry relevant certifications and educationAccident and Term life Insurance
Your key responsibilities
(AI/Chatbot Systems)
Monitor production systems for performance, availability, and anomalies.Troubleshoot and resolve issues related to the AI chatbot, APIs, or infrastructure.Collaborate with development teams for bug fixes and enhancements.Provide application support by handling and consulting on BAU, Incidents/emails/alerts for the respective applications.Act as an escalation point for user issues and requests and from Level 1/L2 support. Report issues to senior management.Manage and mentor regional L1/L2 team to ensure the team is up to speed and picks up the support duties.Gain detailed knowledge of all business flows, the application architecture, and the hardware configuration for supported applications.Define, document, and maintain procedures, SLAs, and knowledge base to support the platforms to ensure consistent service levels are achieved across the global support team.Build and maintain effective and productive relationships with the stakeholders in business, development, infrastructure, and third-party systems / data providers.Manage incidents through resolution, keeping all stakeholders abreast of the situation and working to minimize impact wherever possible.Conduct post-mortems of incidents and drive relevant feedback into Incident, Problem and Change management programs.Facilitate coordination across L1/L2 and L3/Engineering teams to investigate and resolve an ongoing infrastructure/platform or application issue impacting multiple business lines.Drive the development and implementation of the tools and best practices needed to provide effective support.Collaborate with and deliver initiatives and install these initiatives to drive stability in the environment.Assist in the process to approve all new releases and production configuration changes; ensure development includes all necessary documentation for each change and conduct post-release testing where required.Perform reviews of all open production items with the development team and push for updates and resolutions to outstanding tasks and reoccurring issues.Regularly review and analyze service requests and issues that are raised; seek to improve the process and remove reoccurring tasks where possible.Perform reviews of existing monitoring for the platform and make improvements where possible.The candidate will have to work in shifts as part of a Rota covering EMEA hours and in the event of major outages or issues we may ask for flexibility to help provide appropriate cover.
Your skills and experience
5+ years hands on IT support and interacting with application end users.Good analytical and problem-solving skills.Exceptional written and oral communication skills, including the ability to communicate technical information to a non-technical audience and at executive levels.Understanding of ITIL / best practices for supporting a production environmentPreferredITIL v3 foundation certification.PreferredExperience in a financial institution or large corporation; good technology background.PreferredPrior experience working in chatbot based communication model or project.Understanding of how to get things done in large organizations, where to use processes and how to build and operate a network.Ability to work across countries, regions, and time zones with a broad range of cultures and technical capability.
Technical competency
Cloud Technologies:
Hands-on experience with Google Cloud Platform (GCP).Strong understanding of Google Cloud Run for managing serverless containerized applications.Proficiency in configuring and managing Google Observability tools (Cloud Monitoring, Logging, and Error Reporting).
DevOps Tools:
Expertise in GitHub Actions for CI/CD pipelines.Experience with GitHub for version control and collaboration.
AI/ML and Chatbot Frameworks[Good to have]
Experience with Dialogflow for building and optimizing chatbot applications.Knowledge of Google Moderation API and sensitive data removal services for content safety and compliance.
Incident and Operations Management:
Familiarity with incident management processes for high-criticality systems.Strong skills in monitoring application performance, troubleshooting, and root cause analysis.
Soft
Skills:
Excellent problem-solving abilities in high-pressure scenarios.Strong communication skills to work effectively with stakeholders and cross-functional teams.Ability to prioritize tasks and manage time effectively in a fast-paced environment.
How well support you
