Description

You will design, develop, and implement Generative AI models and applications, focusing on building and optimizing Retrieval-Augmented Generation (RAG) systems.

Responsibilities

• Develop and implement Generative AI models, integrating and managing vector databases for RAG systems.
• Apply ML concepts, including model fine-tuning, and deploy solutions via APIs built with FastAPI using containerization.
• Perform data engineering tasks to prepare and manage data pipelines for AI model training and evaluation.
• Utilize advanced prompt engineering techniques to optimize LLM interactions and expose capabilities via APIs.
• Collaborate with teams to integrate AI solutions into products on GCP, adhering to MLOps and CI/CD practices.

Required Skills

• 3+ years of software engineering experience focused on Generative AI or Machine Learning.
• Proficiency in Python Programming.
• Expertise in prompt engineering techniques for Large Language Models (LLMs).
• Proven experience building and deploying RAG systems using Vector Databases.
• Hands-on experience with Google Cloud Platform (GCP) services for AI/ML.
• Experience developing APIs, specifically with FastAPI.
• Proficiency with version control systems (Git).
• Experience with containerization technologies (Docker).
• Solid experience with SQL for data manipulation and querying.

Key Skills

Education

Bachelor's degree