AI Lead Engineer

Who You Are:

As an AI Lead Engineer on Citian’s Data Success team, you make sure our state and local government clients’ data gets into Citian quickly, completely, and accurately. Every agency stores its crash, roadway, and asset data differently: legacy databases, GIS layers, spreadsheets, scanned PDFs, and police report narratives. You use AI to turn that variety into clean, standardized data that powers our CRASH and ADAPT products. You build and run the ingestion and extraction pipelines, apply LLMs and computer vision where they speed up the work, and put checks in place that prove the output is right. You work directly with agency GIS, IT, and engineering staff, and you can explain data problems clearly to a traffic engineer and a software engineer alike. You’re resourceful, care about getting the details right, and want your work to have a direct impact on making roads safer.

Expected Duties:

• Own data ingestion for new and existing state and local government clients, from first data request to production-ready data in Citian’s products.
• Work directly with agency GIS, IT, and engineering staff to understand their data sources, gain access, and resolve gaps or inconsistencies.
• Build and maintain pipelines that pull data from client systems, including databases, APIs, Esri/ArcGIS services, open data portals, and file transfers.
• Apply LLMs and AI to extract structured data from unstructured sources, such as crash report narratives, scanned documents, PDFs, and engineering plans.
• Use AI-assisted schema mapping and data cleaning to bring each agency’s data onto Citian’s standard data model, cutting the time it takes to onboard new clients.
• Lead computer vision and image recognition work to extract roadway and infrastructure assets from imagery and other geospatial sources.
• Build automated QA/QC checks that validate AI outputs against source data and domain standards, so every dataset that ships can be trusted.
• Handle sensitive client data, including personal information in crash records, according to data sharing agreements and Citian’s security standards.
• Evaluate third-party AI tools, APIs, and models for extraction work, weighing build vs. buy tradeoffs with Engineering.
• Document data sources, mappings, and processes for each client so onboarding is repeatable and scalable.
• Partner with Customer Success, Account Management, and Product to set data timelines, communicate data issues, and feed client needs back into the roadmap.

Required Skills & Experience:

• Bachelor’s degree in Computer Science, Data Science, Engineering, GIS, or a related field.
• 5+ years of professional experience in data engineering, AI/ML engineering, or a related role.
• 2+ years of hands-on experience applying AI or machine learning to real-world data, ideally in a product environment.
• Strong proficiency in Python and SQL for building data pipelines and transforming data.
• Hands-on experience using LLMs for document processing or structured data extraction, including prompting, tool use, and evaluating output quality.
• Experience ingesting data from diverse and messy sources, including databases, APIs, spreadsheets, and unstructured documents.
• Experience with AWS services such as S3, Lambda, and related data tools.
• Experience working with geospatial data and tools, such as ArcGIS, PostGIS, or GeoPandas.
• Experience building data validation and quality checks.
• Excellent communication skills, with the ability to work directly with external clients and explain technical issues to non-technical audiences.

Salary Range: $150,000 - 250,000