AI Engineer AWS Bedrock, LLMs, and Conversational AI

About

We are looking for a highly skilled AI Engineer with expertise in building advanced AI-driven applications using AWS Bedrock and large language models (LLMs). The ideal candidate will have hands-on experience in prompt engineering, agent building, and Conversational AI Generation (CAG) to create intelligent, context-aware AI agents. You will leverage Python and FastAPI to develop scalable APIs, implement Retrieval-Augmented Generation (RAG), and work with vector databases to optimize AI-driven search and response systems. This role requires strong collaboration with cross-functional teams to deliver innovative AI solutions on AWS.

Key Responsibilities:

• Design, develop, and deploy AI applications leveraging AWS Bedrock and other AWS AI/ML services.
• Engineer effective prompts and prompt templates to optimize LLM performance and contextual understanding.
• Build and maintain intelligent AI agents capable of multi-turn conversations and task automation using Conversational AI Generation (CAG) techniques.
• Develop scalable APIs using Python and FastAPI to serve AI models and conversational agents.
• Implement Retrieval-Augmented Generation (RAG) frameworks to enhance knowledge retrieval and response accuracy.
• Manage and optimize vector databases (e.g., Pinecone, Weaviate) for semantic search and similarity matching.
• Design and apply scoring and ranking algorithms to improve LLM output relevance and user experience.
• Collaborate closely with data scientists, software engineers, and product managers to integrate AI capabilities into products.
• Optimize AI workflows and infrastructure on AWS for scalability, security, and cost-efficiency.
• Stay current with emerging AI technologies, prompt engineering best practices, and AWS innovations.

Required Skills and Qualifications:

• Proven experience with AWS Bedrock and AWS AI/ML ecosystem.
• Strong proficiency in Python programming, with practical experience using FastAPI for API development.
• Expertise in prompt engineering to design, test, and refine prompts for LLMs.
• Experience building AI agents and conversational AI systems using CAG methodologies.
• Working knowledge of Retrieval-Augmented Generation (RAG) and its application in AI solutions.
• Hands-on experience with vector databases such as Pinecone, Weaviate, or similar platforms.
• Familiarity with scoring and ranking techniques for large language model outputs.
• Solid understanding of AWS cloud infrastructure components including IAM, Lambda, S3, and EC2.
• Excellent collaboration skills within agile, cross-functional teams.
• Strong analytical and problem-solving abilities.
• Effective communication skills to convey complex AI concepts clearly.

Preferred Qualifications:

• Experience with Hugging Face Transformers or similar LLM frameworks.
• Knowledge of containerization (Docker) and orchestration tools (Kubernetes).
• Familiarity with CI/CD pipelines for AI/ML model deployment.
• Background in NLP, dialogue systems, or human-computer interaction.