Overview
As a GenAI / LLM Engineer, you will play a critical role in delivering a robust Generative AI solution for a regulated financial services sector. Collaborating with a team of engineers, you will be responsible for implementing enhancements and ensuring the smooth operation of LLM pipelines, document processing, and agentic AI technologies, leveraging AWS resources. Your expertise will help transition GenAI solutions from conception to production within a complex regulatory framework.
Responsibilities
- Develop and implement production-grade Generative AI solutions using AWS technologies.
- Support the delivery and enhancement of LLM pipelines and document processing systems.
- Utilize Amazon Bedrock and OpenSearch for efficient data management and retrieval.
- Design multi-agent architectures and tool-use frameworks for AI applications.
- Oversee RAG architecture for handling complex, document-heavy applications.
- Evaluate GenAI performance, focusing on hallucination detection and confidence scoring.
- Ensure compliance with data handling and security requirements in regulated environments.
Requirements
- Proven experience in delivering production-level GenAI/LLM solutions, not just prototypes or POCs.
- Strong knowledge of RAG architecture for complex applications.
- Proficiency with Amazon Bedrock or equivalent managed LLM platforms.
- Experience with Amazon OpenSearch, particularly in vector search and hybrid retrieval.
- Solid Python development skills and familiarity with relevant frameworks like LangChain and LlamaIndex.
- Hands-on knowledge of document processing technologies such as Amazon Textract and PyPDF.
- Experience in the financial services sector or other regulated environments concerning sensitive data and compliance requirements.
- Understanding of information security, audit trails, and PII handling practices.