Description

Lead the design, architecture, and implementation of data pipelines and AI systems on Google Cloud Platform.

Responsibilities

• Design and implement data pipelines using BigQuery, Dataflow, and Cloud Storage for efficient ingestion and transformation.
• Develop Retrieval-Augmented Generation (RAG) techniques to combine knowledge retrieval with generative models.
• Implement prompt engineering strategies to maximize LLM performance, accuracy, and relevance.
• Evaluate and select appropriate models such as BERT, GPT-3, or PaLM based on project requirements.
• Mentor junior engineers and contribute to best practices for secure, scalable AI systems on GCP.

Required Skills

• 10+ years of professional experience in software engineering or data architecture.
• Expertise in Google Cloud Platform (GCP) services, specifically Vertex AI.
• Hands-on experience with Large Language Models (LLM) and Generative AI.
• Proficiency with BigQuery, Dataflow, and Cloud Storage.
• Deep understanding of Retrieval-Augmented Generation (RAG) architectures.
• Strong knowledge of NLP concepts and techniques.
• Experience with cloud-native architectures and DevOps principles.
• Proven ability to translate business requirements into scalable AI solutions.

Preferred Skills

• Relevant certifications in Google Cloud Platform or Generative AI technologies.
• Experience with application development.

Key Skills

Education

Any Graduate