Senior Staff / Senior Machine Learning Engineer

On-siteDefense, Intelligence, & Space SolutionsBoulder, Colorado, United States; United States; On-site; USD 140,000 - 210,000; Full time

Job summary

SciTec, a wholly owned subsidiary of Firefly Aerospace, is seeking a Staff/Senior Staff Machine Learning & AI Engineer in Boulder, CO to design, train, and optimize high‑performance ML models for TO support of national defense. You will work on end‑to‑end ML pipelines for OPIR sensor data within a Linux production environment.

The role requires collaboration with C++ and system engineers in an Agile team, focusing on scalable, reproducible AI solutions and robust software practices for

Responsibilities

• Develop and implement machine learning, deep learning, and AI algorithms for remote sensor data exploitation
• Design, train, and optimize models supporting image analysis, detection, tracking, and multi‑modal sensor fusion
• Deploy high‑performance inference pipelines for large‑volume, real‑time or near‑real‑time data processing
• Collaborate closely with C++ and system‑level engineers to integrate ML/AI solutions into existing software frameworks
• Apply strong software engineering practices to ensure model reproducibility, performance, and maintainability
• Work as part of an Agile team and contribute to shared tools, workflows, and documentation
• Other duties as assigned

Job description

Description

SciTec, a wholly owned subsidiary of Firefly Aerospace, is a dynamic non-traditional defense contractor that delivers advanced technologies in support of U.S. National Security and Defense. For the past forty-five plus years, we have supported Department of Defense customers by developing innovative remote sensing algorithms, tools, and techniques to deliver world-class data exploitation capabilities supporting missile

Important Notice: SciTec exclusively works on U.S. government contracts that require U.S. citizenship for all employees. SciTec cannot sponsor or assume sponsorship of employee work visas of any type. Further, U.S. citizenship is a requirement to obtain and keep a security clearance. Applicants that do not meet these requirements will not be considered.

SciTec has an immediate opportunity for a talented Machine Learning & AI Engineer to support our programs delivering Next-Generation Missile Warning software. This is a unique opportunity to join a small business delivering core capabilities for national defense. You will work within a fast‑paced team developing end‑to‑end machine learning and analytics pipelines for Overhead Persistent InfraRed (OPIR) sensor data supporting Missile Warning, Missile Defense, Battlespace Awareness, and Technical Intelligence.

We are seeking a Staff/Senior Staff Machine Learning & AI Engineer to design, train, and optimize high‑performance ML models and algorithms that enhance remote sensor data exploitation and analysis. This role focuses on hands‑on algorithm development, model optimization, and integration into production software systems running on Linux.

The ideal candidate is a strong individual contributor with deep experience in machine learning, high‑throughput data processing, and applied algorithmic development. Success in this role requires technical curiosity, rigorous engineering practices, and the ability to collaborate effectively within a highly technical, Agile team.

Responsibilities

• Develop and implement machine learning, deep learning, and AI algorithms for remote sensor data exploitation
• Design, train, and optimize models supporting image analysis, detection, tracking, and multi‑modal sensor fusion
• Deploy high‑performance inference pipelines for large‑volume, real‑time or near‑real‑time data processing
• Collaborate closely with C++ and system-level engineers to integrate ML/AI solutions into existing software frameworks
• Apply strong software engineering practices to ensure model reproducibility, performance, and maintainability
• Work as part of an Agile team and contribute to shared tools, workflows, and documentation
• Other duties as assigned