we are seeking an experienced AI Engineer to lead the development of our AI-powered legal research and document analysis platform for environmental litigation. The platform helps attorneys accelerate complaint drafting, identify Potentially Responsible Parties (PRPs), and synthesize insights from thousands of FOIA documents related to PFAS contamination and CERCLA cases.
Key Responsibilities
AI/ML Development
• Design and implement RAG (Retrieval-Augmented Generation) pipelines for querying and synthesizing information from large document corpora (FOIA documents, EPA records, regulatory filings)
• Build agentic AI workflows that route queries across multiple data sources including EPA ECHO database, regulations.gov, web searches, and internal document stores
• Develop MCP (Model Context Protocol) integrations for accessing EPA and regulatory data programmatically
• Implement document generation capabilities including complaint drafting, expert affidavits, and legal memos using LLMs
• Build PRP identification and scoring models to prioritize potentially liable parties for litigation
• Create topography mapping systems for contamination discovery and case prioritization
Platform Engineering
• Migrate and containerize the existing Streamlit application from Snowflake to AWS (Fargate, Lambda, S3)
• Implement authentication and access control using AWS Cognito with OIDC integration
• Build CI/CD pipelines and infrastructure-as-code for automated deployments
• Optimize for performance—eliminate cold starts, reduce latency, and ensure responsive user experience
• Design secure document access patterns (replacing pre-signed URLs with direct Fargate-to-S3 access)
Product & UX
• Build intuitive interfaces for document querying, report generation, and source citation/linking
• Implement markdown rendering, document viewing, and seamless integration with existing workflows
• Design user session management, prompt history retrieval, and usage analytics
Required Qualifications
• 5+ years of experience building production AI/ML systems, with deep expertise in LLMs and NLP
• Strong experience with RAG architectures, vector databases (Pinecone, Weaviate, pgvector), and embedding models
• Proficiency in Python with frameworks like LangChain, LlamaIndex, or similar orchestration tools
• Experience with AWS services: Lambda, Fargate/ECS, S3, Cognito, API Gateway
• Hands-on experience with Streamlit or similar Python-based web frameworks
• Strong understanding of containerization (Docker) and CI/CD practices
• Excellent communication skills and ability to translate technical concepts for non-technical stakeholders
Preferred Qualifications
• Experience with agentic AI patterns and multi-step reasoning workflows
• Familiarity with legal tech, document automation, or regulatory compliance domains
• Experience with MCP (Model Context Protocol) or similar tool-use frameworks
• Background in information extraction, entity recognition, or knowledge graph construction
• Experience with Snowflake, data pipelines, or ETL workflows
• Familiarity with EPA data sources (ECHO, TRI, Envirofacts) and environmental regulations
Tech Stack
Languages: Python, JavaScript/TypeScript
AI/ML: OpenAI/Anthropic APIs, LangChain, Vector DBs, Embedding Models
Cloud: AWS (Fargate, Lambda, S3, Cognito, API Gateway), Snowflake
Frontend: Streamlit, React (future)