Production Support Engineer

Position : Production Support Engineer AI & Agentic Systems

Experience: 3 - 5 years

Job Description:

We are seeking a Production Support Engineer who thrives on technical discovery and problem-solving. This is a high-impact role that bridges traditional backend production support with modern AI engineering.

You will be responsible for maintaining the stability of a high-concurrency Python environment, troubleshooting complex Snowflake data flows, and refining AI agent behavior in real time.

Key Responsibilities

Agentic Oversight

Monitor and debug multi-agent orchestration using Google ADK

Ensure tool-calling accuracy and correct logic flow within agent frameworks

Incident Management

Triage and resolve production issues in a high-concurrency FastAPI and Python (Async) backend

Own issues end-to-end, from identification to resolution

Data Integrity

Execute and optimize SQL queries in Snowflake

Validate data consistency and resolve discrepancies

AI Reliability

Identify and mitigate LLM hallucinations and logic errors

Improve system accuracy through Prompt Engineering

Leverage Vertex AI observability tools for monitoring and diagnostics

Full-Stack Troubleshooting

Support UI/UX debugging in React and TypeScript

Ensure smooth integration between AI backend services and the frontend

Cloud Operations

Manage and support services within the GCP ecosystem

Work specifically with Vertex AI, Discovery Engine, and Cloud Run

Technical Profile

We prioritize strong problem-solving ability and technical curiosity over a perfect match in years of experience. If you have the foundational skills and the drive to learn, we encourage you to apply.

Core Competencies

• Backend: Proficiency in Python (Async experience preferred) and FastAPI
• Data: Strong SQL skills with experience in Snowflake or similar cloud data warehouses
• Cloud: Experience with GCP (Vertex AI, Cloud Run) or comparable platforms (AWS/Azure)
• Frontend: Basic familiarity with React and TypeScript for troubleshooting
• AI/LLM: Understanding of Prompt Engineering and Agentic frameworks

Qualifications & Mindset

• Can-Do Attitude: Takes ownership of problems from discovery through resolution
• Curiosity-Driven: Enjoys analyzing and understanding complex systems
• Adaptable: Comfortable working in unfamiliar stacks and learning quickly
• Strong Communicator: Able to clearly explain AI behaviors and technical issues to both technical and non-technical stakeholders