Senior AI Engineer, AI Platform

Kharon•Denver, CO

6d•Hybrid

About The Position

Kharon is seeking a full-time Senior AI Engineer to build and ship AI applications that help businesses understand and manage risks related to global security and international commerce. The position is based in Denver and requires in-office attendance at least three days per week. The engineer will work in rapid, agile cycles to prototype, test, and refine AI models and interfaces, then take successful features from concept through production. This includes integrating advanced AI components, designing data flows and pipelines, writing production-quality code, containerizing services, and deploying systems in secure cloud environments. The role also involves developing internal tools and processes that accelerate development, while ensuring AI systems are monitored, explainable, and aligned with ethical, regulatory, and performance standards. The role partners closely with product managers, designers, engineers, and data scientists to turn complex business challenges into scalable AI systems. Kharon works with complex data concerning global security threats, financial crimes, sanctions, export controls, and threat identification to help clients make informed decisions about business relationships. The company serves leading global financial and multinational institutions. Kharon describes itself as an equal opportunity employer committed to a workplace free from harassment and discrimination. Qualified applicants receive consideration without regard to protected characteristics.

Requirements

Strong software development skills in Python.
Experience with libraries such as LangChain/LangGraph, Agent SDKs, Pydantic, SQLAlchemy/Alembic, and PySpark, Polars, or Pandas.
Experience with tracing systems such as MLFlow or Sentry, RAG systems, memory systems, MCP servers, and agent skills, and knowledge of different models and their tradeoffs.
Strong understanding of how to use AI tools for rapid development, such as Cursor and Claude Code.
Familiarity with containerization using Docker and cloud deployment; AWS is preferred, as is GitHub Actions.
Demonstrated ability to ship high-quality, production-ready ML/AI systems under tight iteration cycles.
Passion for solving complex problems with real-world impact, especially in high-stakes or regulated domains.
Excellent communication skills and ability to thrive in cross-functional, mission-driven environments.

Nice To Haves

Bachelor's or master's degree in Computer Science, Artificial Intelligence, Engineering, or a related field (preferred).
Familiarity with AWS cloud deployment.
Familiarity with GitHub Actions.

Responsibilities

Design, develop, and ship proof-of-concept AI applications within days or weeks.
Work in fast, agile cycles to test ideas, gather feedback, and refine models and interfaces.
Build and integrate advanced AI components, including Model Context Protocol clients and servers, foundation model fine-tuning, and multi-agent orchestration frameworks.
Take features from idea to production by architecting data flows, writing high-quality code, containerizing services, and deploying them in secure cloud environments such as AWS.
Partner with product managers, designers, engineers, and data scientists to translate abstract business problems into concrete, scalable AI systems.
Develop production-grade data pipelines that integrate data to and from AI systems.
Develop and maintain internal tools to speed up development cycles, including CI/CD scripts, evaluation harnesses, dashboards, and secure sandbox environments.
Ensure AI systems are monitored, explainable, and aligned with ethical, regulatory, and performance standards.
Stay current with AI/ML advancements, evaluate open-source frameworks, and share best practices across the team.