Description

You will build and deploy production-grade GenAI and LLM applications on Google Cloud Platform.

This role is on-site.

Responsibilities

• Develop GenAI/LLM applications in Python, handling prompt engineering and response workflows for production.
• Build and integrate REST APIs using FastAPI or Flask to expose LLM capabilities to downstream services.
• Deploy and manage AI services on GCP using Vertex AI, ensuring operational readiness and scalability.
• Containerize services with Docker and Kubernetes, managing deployment and scaling of AI workloads.
• Collaborate on end-to-end testing and performance validation for AI-powered APIs and model interactions.

Required Skills

• 5.5 to 7 years of relevant experience in Python-based AI engineering.
• Strong proficiency in Python for building application logic and integrations.
• Hands-on experience with GCP and Vertex AI for model hosting and inference.
• Experience with LLM/GenAI development, specifically using Gemini.
• API development skills using REST patterns, FastAPI, or Flask.
• Proficiency in Kubernetes for deploying and operating containerized services.

Preferred Skills

• Experience with Docker for container build and runtime workflows.
• Background in Agentic AI for multi-step or tool-using LLM systems.

Key Skills

Education

Any Graduate