Description

Build, test, and deploy generative AI models and end-to-end applications using Python and AWS services.

Responsibilities

• Develop and deploy generative AI models using LangChain, AWS Bedrock, and other AI frameworks.
• Implement retrieval-augmented generation (RAG) using vector databases like AlloyDB and Aurora PostgreSQL to improve contextual responses.
• Design and optimize prompts through prompt engineering to enhance LLM performance.
• Build end-to-end applications using Streamlit for the frontend and Python for backend services.
• Debug AI models and cloud-based solutions independently within AWS environments.

Required Skills

• 5+ years of experience in software engineering or related fields.
• Proficiency in Python for AI/ML model development, API integration, and cloud deployment.
• Expertise in prompt engineering to craft, test, and optimize LLM outcomes.
• Hands-on experience with Vector Databases, specifically AlloyDB or Aurora PostgreSQL.
• Practical knowledge of retrieval-augmented generation (RAG) and knowledge retrieval techniques.
• Experience implementing search and code ingestion techniques to enhance AI performance.
• Ability to communicate complex AI concepts to non-technical stakeholders.
• Any Graduate degree.

Preferred Skills

• AWS Cloud Certifications, such as AWS Certified Machine Learning or Solutions Architect.
• Proficiency in Java, React, or Angular.
• Deep awareness of emerging Generative AI trends and cloud-based AI innovations.

Key Skills

Education

Any Graduate