Senior AI Software Engineer (TS/SCI)

Vantor•Herndon, VA

6d•Onsite

About The Position

Vantor is seeking a Senior AI/ML Software Engineer to integrate secure chatbot and AI assistant capabilities into existing geospatial intelligence, analytics, visualization, and mission-support tools. You will help analysts discover data, navigate applications, and complete approved workflows using natural language. The role requires strong software engineering skills, practical LLM experience, and an understanding of secure, usable AI in mission environments. To be eligible for this position, you must be a U.S. Citizen. This position requires an active U.S. Government security clearance, applicants who do not currently hold the required clearance will not be eligible for consideration. Employment for cleared roles is contingent upon verification of clearance status. Certain roles may be subject to U.S. export control laws, requiring U.S. person status as defined by 8 U.S.C. 1324b(a)(3). This position requires an active U.S. Government Security Clearance at the TS/SCI with CI poly level.

Requirements

Bachelor’s degree in computer science, software engineering, artificial intelligence, data science, or a related field, or equivalent experience.
8+ years of professional software engineering experience delivering production applications or services.
Hands-on experience integrating generative AI or LLMs into production software applications using patterns such as RAG, embeddings, vector search, function calling, or agent workflows.
Strong Python skills and experience with JavaScript, TypeScript, Java, Go, C++, or another modern language.
Experience building REST APIs or microservices and using Git, automated testing, CI/CD, and Agile development practices.
Experience integrating enterprise data sources and applying secure identity, authorization, and data-protection controls.
Willingness to work 75% or as needed in a SCIF environment in Herndon, VA; Denver, CO; or St. Louis, MO.
U.S. Person with an active TS/SCI with CI poly, or the ability to obtain the required clearance and polygraph.

Nice To Haves

Experience building chatbot interfaces with React, TypeScript, or comparable web frameworks and applying usability practices.
Experience with AI orchestration frameworks, model gateways, MCP-compatible services, or agent-to-tool integration.
Experience deploying commercial, open-source, or locally hosted LLMs in cloud, on-premises, classified, air-gapped, or disconnected environments.
Experience with vector search, Elasticsearch, knowledge graphs, GIS, imagery, geospatial applications, or other mission-critical systems.
Experience with AI safety controls, human-in-the-loop approvals, model monitoring, evaluation, GPU workloads, or model serving.
Experience with containers and Kubernetes; Red Hat OpenShift experience is preferred.

Responsibilities

Integrate AI chatbots and assistants into existing geospatial, analytics, visualization, and mission applications.
Build natural-language workflows for data discovery, application navigation, visualization generation, and approved actions.
Implement LLM patterns such as prompt orchestration, retrieval-augmented generation, tool calling, and conversation context.
Connect AI services to REST APIs, data catalogs, search platforms, knowledge graphs, geospatial services, notebooks, and dashboards.
Develop reusable backend services and frontend components that make AI assistance simple for analysts to use.
Enforce identity, entitlements, and data-access policies; provide citations, provenance, audit records, and clear system limitations.
Test and evaluate AI quality, safety, latency, and usability, including protections against prompt injection, data leakage, and unauthorized actions.
Deploy and operate AI services in Kubernetes and Red Hat OpenShift, including restricted or disconnected environments, and collaborate with technical and customer teams.