Key Responsibilities

• Design and implement end-to-end AI pipelines for document ingestion across PDFs, HTML, images, video, and audio
• Build multimodal extraction workflows using OCR, layout parsing, and vision-language models
• Develop LLM-driven compliance reasoning systems
• Build scalable retrieval-augmented generation (RAG) systems grounded in regulatory content

Requirements

• 8 years of experience in software engineering, machine learning, or applied AI
• Proven track record of building and deploying production-grade AI/ML systems
• Experience in regulated industries such as finance, legal, or healthcare strongly preferred
• Strong expertise in natural language processing and large language models
• Hands-on experience with retrieval-augmented generation (RAG)
• Experience with model evaluation, benchmarking, and performance testing
• Familiarity with multimodal AI, including text, image, and layout understanding
• Strong Python development experience
• Experience with LLM orchestration or agent frameworks such as LangChain or AWS Strands
• Experience with vector databases such as PGVector or Pinecone
• Familiarity with document processing pipelines, including OCR and PDF parsing tools
• Experience with cloud platforms such as AWS, GCP, or Azure
• Knowledge of MLOps, CI/CD pipelines, model monitoring, and deployment best practices
• Strong background in scalable system design and distributed architectures
• Must be authorized to work in the US: USC, GC, or EAD

Skills Required