AI Full Stack Engineer (Python + GCP + LLMs)

About the Role:

We are looking for a hands-on AI Full Stack Engineer who can build scalable applications and integrate advanced AI capabilities. This role is ideal for someone with strong Python backend experience, working knowledge of modern frontend frameworks, and real-world exposure to LLM-based systems.

Tasks

Key Responsibilities:

• Build and scale backend systems using Python (FastAPI / Flask)

• Develop and integrate AI-powered features using LLMs and generative AI

• Design and consume REST APIs with proper authentication (JWT/OAuth)

• Work with GCP services (Cloud Run, Pub/Sub, Firestore, Vertex AI)

• Develop frontend components using React or similar frameworks

• Implement scalable architectures (microservices / event-driven systems)

• Optimize performance and ensure production-grade reliability

Requirements

Must-Have Requirements (Screening Filter):

• 3+ years of experience in Python backend development

• Hands-on experience with FastAPI or Flask in production

• Experience working with LLMs / Generative AI APIs (OpenAI, etc.)

• Practical exposure to GCP (Cloud Run / GKE / Pub

Sub / Vertex AI)

• Experience building and consuming REST APIs

• Familiarity with databases (SQL/NoSQL)

• Experience with Docker and deployment workflows

Benefits

• Experience working with voice-based AI solutions or conversational AI platforms.

• Familiarity with AI orchestration frameworks or LLM integrations.

• Experience with real-time systems, streaming, or event-driven architecture.

Important Note:

This is not a generic MERN/full stack role. Candidates without Python backend + AI/LLM + GCP experience will not be considered.