Description

You will develop Generative AI applications in Python using Large Language Models and cloud-native services on GCP.

This role is on-site.

Responsibilities

• Implement Retrieval-Augmented Generation (RAG) workflows, including document ingestion, retrieval, and response generation.
• Design and iterate prompts for production use, including prompt engineering and evaluation-driven improvements.
• Build and integrate AI features into backend services and APIs, ensuring correctness and performance.
• Collaborate on deployment, monitoring, and operational readiness of GenAI services on GCP.

Required Skills

• 4-7 years of relevant experience in Python and Generative AI development.
• Strong proficiency in Python for building LLM-based applications and backend services.
• Hands-on experience with GCP (Google Cloud Platform) for deploying and operating GenAI solutions.
• Proven experience with RAG architectures and prompt engineering for production-grade outputs.
• Experience developing with Large Language Models (LLMs).

Preferred Skills

• Agentic AI experience and building agent workflows.
• LLM-focused development experience, including fine-tuning, orchestration, or evaluation.

Key Skills

Education

Any Graduate