Source description
About the role
AI Engineer – AWS Generative AI & Conversational AI Role Overview We are seeking an AI Engineer with hands-on experience in Generative AI and AWS AI services to design and build intelligent applications such as enterprise chatbots, knowledge assistants, and AI-powered automation solutions . The ideal candidate will have strong Python development skills and experience integrating Large Language Models (LLMs) with enterprise systems using AWS services . This role will work closely with product, data engineering, and platform teams to develop scalable AI-powered conversational solutions using AWS services such as Bedrock, API Gateway, and Lambda , exposing AI capabilities as secure microservices for enterprise consumers .
Key Responsibilities Generative AI Development
Design and build AI-powered chatbots and conversational assistants using LLMs. Develop solutions using AWS Bedrock models including Anthropic Claude Sonnet . Implement Retrieval Augmented Generation (RAG) architectures for enterprise knowledge retrieval. Integrate LLMs with enterprise data sources such as databases, APIs, document repositories, and knowledge bases .
AWS AI Platform Development
Develop AI applications using AWS Bedrock, SageMaker, Lambda, API Gateway, Step Functions, and S3 . Build scalable Python-based microservices using FastAPI or similar frameworks . Expose AI capabilities as secure APIs through AWS API Gateway for internal and external consumers . Implement authentication, rate limiting, and secure API access patterns.
Conversational AI Engineering
Design conversational workflows and prompt engineering strategies. Manage session context and multi-turn interactions for chatbot applications. Implement guardrails to mitigate hallucinations and enforce enterprise policies .
Data & Knowledge Integration
Build ingestion pipelines for structured and unstructured data including PDFs, documents, and databases . Implement vector search and knowledge retrieval systems using OpenSearch, Pinecone, FAISS, or similar technologies.
AI Operations & Monitoring
Monitor model performance, latency, and usage costs. Implement logging, evaluation frameworks, and observability for LLM-based systems. Continuously improve prompt strategies and retrieval pipelines.
Required Skills Core Technical Skills
Strong programming experience in Python Experience building APIs using FastAPI, Flask, or similar frameworks Hands-on experience with microservices architecture
More at myridius