Overview
The AI Engineer will support the delivery of a production-grade Generative AI solution in a regulated financial services environment. This hands-on engineering role will focus on developing LLM pipelines and implementing document processing and agentic AI technologies using AWS. The engineer will work closely with cross-functional teams to transition GenAI solutions from concept to production.
Responsibilities
- Develop and implement Generative AI solutions within a production environment.
- Design and optimize LLM pipelines for effective document processing.
- Utilize AWS technologies, including Amazon Bedrock and OpenSearch, for solution delivery.
- Create and maintain RAG architectures for complex applications.
- Integrate document processing tools such as Amazon Textract and PyPDF.
- Evaluate GenAI solutions for effectiveness, including validation and detection techniques.
- Collaborate with teams to ensure compliance with regulatory standards.
Requirements
- Proven experience delivering production-ready Generative AI/LLM solutions.
- Strong knowledge of RAG architecture for document-intensive applications.
- Experience with Amazon Bedrock or a similar managed LLM platform.
- Proficiency in Amazon OpenSearch, including vector search and hybrid retrieval.
- Solid Python development skills and experience with relevant frameworks like LangChain or LlamaIndex.
- Familiarity with document processing technologies and multi-agent architecture design.
- Experience working within financial services or similarly regulated environments.
- Understanding of data security, including PII handling and audit requirements.