About the role
Job Description
We are looking for an experienced Python & GCP AI Support Engineer to provide end-to-end production support for AI-powered applications running on Google Cloud Platform. The ideal candidate will have experience supporting AI/ML solutions, troubleshooting cloud-based applications, working with Python APIs, and collaborating with business stakeholders to ensure service reliability and continuous improvement.
Mandatory Skills
- Strong experience with Python development and support
- Hands-on experience with Google Cloud Platform (GCP)
- Experience with Google ADK (Agent Development Kit)
- Hands-on experience with Vertex AI Gemini
- Strong knowledge of BigQuery and SQL
- Experience with FastAPI
- Experience with React and TypeScript
- Experience with Document AI
- Knowledge of Cloud Run and Cloud Workflows
- Experience with PingOne OIDC or OAuth/OpenID Connect authentication
- Knowledge of AI Evaluation Frameworks and LLM quality monitoring
- Experience troubleshooting production applications and performing Root Cause Analysis (RCA)
- Strong stakeholder communication and incident management skills
Roles & Responsibilities
- Own end-to-end L1, L2, and L3 production support for the Lease Assist platform.
- Serve as the primary technical point of contact for Irvine and Qvest.
- Manage business communications, including user query intake, status updates, issue resolution, and stakeholder coordination.
- Perform incident triage and Root Cause Analysis (RCA) across FastAPI services, Google ADK agents, BigQuery, Document AI pipelines, and React applications.
- Monitor AI agent quality by reviewing chat feedback, identifying hallucinations, and recommending improvements for Router, Standard Agent, and Deep Research models.
- Monitor production environments including Cloud Run, Cloud Workflows, Vertex AI Gemini, and BigQuery performance, while proactively identifying and resolving issues.
- Conduct weekly service reviews, prepare monthly governance reports, and maintain operational runbooks and support documentation.
- Collaborate with development, AI, and cloud engineering teams to improve platform stability, performance, and reliability.
Preferred Skills
- Experience supporting Generative AI or LLM-based applications.
- Familiarity with monitoring and observability tools.
- Experience working in Agile/Scrum environments.
- Strong analytical and problem-solving skills.
- Excellent verbal and written communication skills.
- Ability to manage multiple priorities in a fast-paced production support environment.