Overview
The GenAI / LLM Engineer will play a crucial role in delivering a production-grade Generative AI solution tailored for a regulated financial services environment. Working fully remotely, the contractor will leverage AWS technologies, focusing on LLM pipelines, RAG, document processing, and agentic AI, while bringing their expertise in moving proof-of-concept solutions into real-world applications.
Responsibilities
- Support the delivery of Generative AI solutions in a production environment.
- Develop and implement LLM pipelines and RAG architectures.
- Utilize document processing technologies to enhance application functionality.
- Collaborate with stakeholders to ensure compliance with regulatory requirements.
- Employ AWS technologies, including Amazon Bedrock and OpenSearch, for system architecture.
- Design multi-agent or tool-use architectures for complex applications.
- Conduct evaluation and validation of GenAI outputs, including hallucination detection.
Requirements
- Strong hands-on experience in delivering production-grade GenAI/LLM solutions.
- Proficient in RAG architecture for document-heavy applications.
- Experience with Amazon Bedrock or similar managed LLM platforms.
- Knowledge of Amazon OpenSearch, including vector search and hybrid retrieval.
- Strong development skills in Python programming.
- Familiarity with frameworks like LangChain, LlamaIndex, or similar.
- Experience with document processing technologies such as Amazon Textract.
- Understanding of compliance and security requirements in financial services environments.