AI/ML Engineer - ELSYS - Colorado Springs, CO - (Open Rank)
Role details
Job location
Tech stack
Job description
The Electronic Systems Laboratory (ELSYS) at the Georgia Tech Research Institute (GTRI) is seeking an AI/ML Engineer to support the United States Space Force (USSF) Space Systems Command (SSC). This position directly supports the USSF portfolio, specifically the Operational Test and Training Infrastructure (OTTI) / System Delta 81.
This role centers on "physical AI" for space systems-AI tightly coupled to high fidelity, physics-based satellite simulations and live operational data. The selected candidate will help build and integrate digital twin-style environments (e.g., NVIDIA-based simulation stacks) that remain time-aligned with real satellite telemetry and sensor data, enabling realistic test, training, and evaluation of AI capabilities for space operations.
While the broader AI/ML engineering discipline encompasses algorithm development, this specific position focuses heavily on the foundational data, interoperability, and simulation architectures required to deploy and evaluate advanced AI and Large Language Model (LLM) capabilities within DoD space simulation and live environments. Working in direct support of OTTI physical AI and emerging technology efforts, this role is responsible for engineering the critical data infrastructure, semantic ontologies, robust API abstraction layers, and advanced data pipelines that connect digital twins, AI training/evaluation workflows, and live systems., The Artificial Intelligence/Machine Learning (AI/ML) Engineer develops AI/ML algorithms, cloud computing, and/or heterogeneous distributed computing infrastructures to support the deployment of AI/ML applications. The AI/ML Engineer also researches the mathematical foundations and frameworks for nonlinear systems characterized by time-varying and emerging dynamics of evolving or adaptive systems. The AI/ML Engineer develops technical solutions at the leading edge of Artificial Intelligence, Machine Learning, Genetic Programming, Computer Vision, and advanced data processing, filtering, and fusion techniques in high-performance computing and distributed heterogeneous computing environments. The AI/ML Engineer writes parallel processing programs to deploy ML models developed by data scientists into more complex systems. The AI/ML Engineer has familiarity with state-of-the-art, open-source software frameworks and high-performance computing accelerators for machine learning. When conducting research, the AI/ML Engineer leverages the most recent advances in statistical analysis of large data sets to advance state-of-the-art automated sensor and data processing for a broad range of intelligent and sensor-enabled systems. Key Responsibilities
- Design complex system architectures (e.g., high-performance computing clusters, networks, chipsets, GPUs) based on available hardware (e.g., embedded systems, cloud, on-premise, etc.)
- Lead a team of engineers responsible for system deployment
- Develop novel algorithms and methodologies
- Engage with sponsors to understand and meet system requirements
- Serve as the primary author on technical reports and proposals
Additional Responsibilities
- Bridge the gap between high-fidelity space simulation environments, AI training workflows, and live systems (e.g., NVIDIA-based digital twin environments) to operationalize AI in widely interoperable test, training, and operational contexts
- Architect and develop API abstraction layers to consolidate and streamline data access across disparate relational, graph, and simulation data services for downstream AI/ML applications
- Design and implement semantic ontologies and data models to standardize complex military datasets, such as the Unified Data Library (UDL), and to enable seamless integration with AI and Large Language Model (LLM) capabilities and orchestration frameworks (e.g., Model Context Protocol)
- Build, optimize, and maintain robust data pipelines that connect live space data sources, UDL datasets, and simulation environments, including ingestion, knowledge graph development, transformation, and vectorization to support Retrieval-Augmented Generation (RAG) and other AI inference workflows
- Translate legacy data systems and unstructured data stores into interoperable, AI-ready formats that can both drive and be driven by physics-based simulations in support of OTTI initiatives
- Develop and maintain comprehensive technical documentation for data schemas, API endpoints, simulation-AI integration patterns, and AI system interoperability frameworks
- Evaluate and integrate emerging commercial and open-source simulation, AI, and data engineering technologies into secure DoD/USSF environments, in coordination with OTTI stakeholders and system architects, Due to our research contracts with the U.S. federal government, candidates for this position must be U.S. Citizens. Clearance Type Required
Candidates must be able to obtain and maintain an active security clearance. Benefits at GTRI
Comprehensive information on currently offered GTRI benefits, including Health & Welfare, Retirement Plans, Tuition Reimbursement, Time Off, and Professional Development, can be found through this link: https://benefits.hr.gatech.edu/. Equal Employment Opportunity
The Georgia Institute of Technology (Georgia Tech) is an Equal Employment Opportunity Employer. The Institute is committed to maintaining a fair and respectful environment for all. To that end, and in accordance with federal and state law, Board of Regents policy, and Institute policy, Georgia Tech provides equal opportunity to all faculty, staff, students, and all other members of the Georgia Tech community, including applicants for admission and/or employment, contractors, volunteers, and participants in institutional programs, activities, or services. Georgia Tech complies with all applicable laws and regulations governing equal opportunity in the workplace and in educational activities.
Equal opportunity and decisions based on merit are fundamental values of the University System of Georgia ("USG") and Georgia Tech. Georgia Tech prohibits discrimination, including discriminatory harassment, on the basis of an individual's race, ethnicity, ancestry, color, religion, sex (including pregnancy), national origin, age, disability, genetics, or veteran status in its programs, activities, employment, and admissions. Further, Georgia Tech prohibits citizenship status, immigration status, and national origin discrimination in hiring, firing, and recruitment, except where such restrictions are required in order to comply with law, regulation, executive order, or Attorney General directive, or where they are required by Federal, State, or local government contract. USG Core Values Statement
Requirements
- Experience developing software in Python for data processing, backend services, or basic machine learning workflows
- Experience working with at least one relational database (e.g., PostgreSQL, MySQL) including schema design and querying
- Experience building and consuming web APIs (e.g., REST or GraphQL) in a production or research environment
- Experience integrating, deploying, testing, and tuning large language models
- Experience implementing data pipelines that perform ingestion, transformation, and preparation of data for analytics or ML (e.g., ETL/ELT workflows)
- Experience with at least one common ML or numerical computing framework (e.g., PyTorch, TensorFlow, Scikit-learn, NumPy) in a coursework, research, or professional context
- Experience using software version control (e.g., Git) in a collaborative environment, * Active TS/SCI Clearance
- Experience working with GPU-accelerated simulation or digital twin environments for robotics, aerospace, or space systems (e.g., NVIDIA Omniverse, Isaac Sim, or similar tools)
- Experience integrating or querying data from the Unified Data Library (UDL) or other large-scale Department of Defense (DoD) or Intelligence Community data repositories
- Familiarity with Space Domain Awareness (SDA), space operations, or Operational Test and Training Infrastructure (OTTI) concepts
- Experience designing or integrating data models and ontologies for complex, multi-source operational data (e.g., sensor data, telemetry, simulation outputs)
- Experience utilizing Large Language Model (LLM) orchestration frameworks (e.g., LangChain, LlamaIndex) for Retrieval-Augmented Generation (RAG) or tool-using agents
- Experience deploying applications or services within DoD DevSecOps platforms (e.g., Platform One) or government cloud environments (e.g., AWS GovCloud, Azure Government)
- Familiarity with Semantic Web standards (e.g., RDF, OWL, SPARQL) for building and mapping robust data ontologies and knowledge graphs
- Experience with containerization and orchestration technologies (e.g., Docker, Kubernetes) in secure or resource-constrained environments
Travel Requirements
10% - 25% travel Education and Length of Experience
This position vacancy is an open-rank announcement. The final job offer will be dependent on candidate qualifications in alignment with Research Faculty Extension Professional ranks as outlined in section 3.2.1 of the Georgia Tech Faculty Handbook
- 5 years of related experience with a Bachelor's degree in Computer Science, Software Engineering, Robotics, Computer Engineering, Data Science, Electrical Engineering, Mathematics, Physics, or a related degree
- 3 years of related experience with a Masters' degree in Computer Science, Software Engineering, Robotics, Computer Engineering, Data Science, Electrical Engineering, Mathematics, Physics, or a related degree
- 0 years of related experience with a Ph.D. in Computer Science, Software Engineering, Robotics, Computer Engineering, Data Science, Electrical Engineering, Mathematics, Physics, or a related degree