Description

You will build and deploy AI-powered applications using Python and Large Language Models on Google Cloud Platform.

This role is on-site.

Responsibilities

• Develop LLM applications with prompt engineering, evaluation, and model customization.
• Build RAG pipelines using vector databases and frameworks like LangChain or LlamaIndex.
• Design agent workflows for multi-step tasks using planning and tool calling.
• Train and deploy ML models for classification, regression, and deep learning tasks.
• Deploy and manage workloads on GCP using Vertex AI, Cloud Run, and GKE.

Required Skills

• 5+ years of experience in Python, NumPy, and Pandas.
• Strong proficiency with Hugging Face ecosystem and LLM integration.
• Experience with PyTorch or TensorFlow for deep learning models.
• Hands-on experience building REST APIs with Flask or FastAPI.
• Databases: PostgreSQL, MySQL, BigQuery, or MongoDB.
• Cloud deployment on Google Cloud Platform (Vertex AI, GKE, Cloud Run).
• Containerization with Docker and Linux environments.
• Version control with Git and SQL querying.

Preferred Skills

• Bachelor’s or Master’s degree in CS, AI, Data Science, or related field.
• Experience with feature engineering and exploratory data analysis.

Key Skills

Education

Bachelor's or Master's degrees