Overview
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
Skills
About RCG Global Services
At Myridius, we transform the way businesses operate. Formerly known as RCG Global Services, our more than 50 years of expertise now drive a new vision—propelling organizations through the rapidly evolving landscapes of technology and business. We offer tailored solutions in AI, data analytics, digital engineering, and cloud innovation, addressing the unique challenges each industry faces. Our integration of cutting-edge technology with deep domain knowledge enables businesses to seize new opportunities, drive significant growth, and maintain a competitive edge in the global market. Our commitment is not just to meet expectations but to exceed them, ensuring measurable impact and fostering sustainable innovation. The success of Myridius is directly tied to the breakthroughs achieved by our clients. Together, we co-create solutions that not only solve today’s challenges but also anticipate future trends. At Myridius, we go beyond typical service delivery. We craft transformative outcomes that help businesses not just adapt, but thrive in a world of continuous change. Discover how Myridius can elevate your business to new heights of innovation. Visit us at www.myridius.com and start leading the change.