Job Summary
We are seeking a Lead AI Engineer to design and build an AI-powered compliance screening platform that evaluates communications for adherence to regulatory standards and industry guidelines. This role sits at the intersection of artificial intelligence, regulatory compliance, and risk management and will lead the development of systems that analyze content across formats including PDFs, emails, social media, and video to generate auditable and explainable compliance decisions.
Key Responsibilities
• Design and implement end-to-end AI pipelines for document ingestion, multimodal extraction, and LLM-driven compliance reasoning.
• Build document ingestion pipelines supporting PDFs, HTML, images, video, and audio.
• Implement multimodal extraction using OCR, layout parsing, and vision-language models.
• Build scalable Retrieval-Augmented Generation (RAG) systems grounded in regulatory content.
• Translate regulatory frameworks into machine-interpretable logic.
• Develop rule classifiers for use cases such as performance claims and disclosures.
• Develop risk scoring models and violation detection workflows.
• Evaluate LLMs for specific compliance actions and use cases.
• Implement prompt engineering, tool usage, and fine-tuning strategies where appropriate.
• Implement guardrails and hallucination mitigation techniques.
• Integrate multimodal models for charts, images, and disclosures.
• Build systems that generate clear, regulator-ready explanations and evidence-backed decisions.
• Ensure AI-driven outputs include full audit trails and traceable evidence linked to applicable rules.
• Define and track model performance metrics including precision, recall, and false negatives.
• Implement human-in-the-loop review workflows.
• Conduct adversarial and edge-case testing to improve model performance and reliability.
• Establish best practices for AI architecture, coding, MLOps, and model governance.
• Collaborate with compliance, legal, and product teams to deliver effective AI solutions.
• Mentor engineering teams on AI/ML engineering practices and technical standards.
Required Qualifications
• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
• 8+ years of experience in software engineering or machine learning.
• Proven track record of building and deploying production AI/ML systems.
• Strong expertise in Natural Language Processing (NLP) and Large Language Models (LLMs).
• Strong experience with Retrieval-Augmented Generation (RAG).
• Strong experience with model evaluation and benchmarking.
• Familiarity with multimodal AI involving text, images, and document layouts.
• Strong Python development experience.
• Experience with LLM orchestration or agent frameworks such as LangChain or AWS Strands.
• Experience with vector databases such as PG Vector or Pinecone.
• Experience with document processing pipelines, OCR, and PDF parsing tools.
• Experience with cloud platforms such as AWS, GCP, or Azure.
• Experience with MLOps, CI/CD pipelines, and model monitoring.
• Experience with scalable system design and distributed architectures.
• Experience with LLM evaluation frameworks; DeepEval preferred.
• Understanding of explainable AI (XAI), auditability, and AI governance requirements.
Preferred Qualifications
• Experience building legal or compliance-focused AI systems.
• Experience working in regulated industries such as finance, legal, or healthcare.
• Familiarity with marketing and advertising review processes.
• Experience analyzing structured and unstructured documents, including charts and disclosures.
• Background in hybrid AI systems combining rules and machine learning.
• PhD in Computer Science, AI/ML, or a related field.