Machine Learning Engineer (2-5 yrs)

Advanced Space•Westminster, CO

23h•$100,000 - $134,000•Hybrid

About The Position

At Advanced Space, we're enabling humanity's return to the Moon and building the technologies that will take us to Mars and beyond. We're looking for a Machine Learning Engineer with 2–5 years of experience to develop innovative ML-driven capabilities that support spacecraft missions, autonomy, navigation, mission planning, and advanced engineering solutions. This is a hands-on technical role focused on translating complex mission and engineering challenges into practical, data-driven solutions. You'll take ownership of technically complex projects from problem formulation and model development through quantitative evaluation, integration, and operational deployment. You'll work with modern machine learning techniques, including statistical learning, probabilistic modeling, optimization, deep learning, and reinforcement learning, to solve real-world aerospace challenges. We're looking for someone who enjoys tackling ambiguous technical problems, has a strong foundation in machine learning and software engineering, and is excited to collaborate across disciplines to develop capabilities that support real space missions. This position is open to U.S. Persons (U.S. citizens or lawful permanent residents) only. Visa sponsorship is not available. Advanced Space exists to enable the sustainable exploration, development, and settlement of space through innovative software, mission services, and technology solutions. As the owner and operator of NASA's CAPSTONE™ mission and the Prime Contractor for AFRL's Oracle mission, we're helping shape the future of cislunar exploration while supporting commercial, civil, and national security customers. Our team combines deep technical expertise with an entrepreneurial mindset. We move quickly, collaborate across disciplines, and empower every engineer to make meaningful contributions. If you're passionate about solving challenging problems and seeing your work fly in space, you'll fit right in.

Requirements

You have a B.S. in Computer Science, Machine Learning, Software Engineering, Aerospace Engineering, or another relevant engineering, physical-science, or quantitative discipline. Equivalent relevant experience may be considered.
You have 2–5 years of professional experience developing and integrating machine learning, optimization, statistical, or data-driven engineering capabilities.
You have demonstrated experience owning technical problems from initial formulation through implementation, quantitative evaluation, documentation, and stakeholder communication.
You are proficient in Python and modern software engineering practices, including version control, code reviews, automated testing, debugging, and performance profiling.
You have experience with at least one modern ML framework, such as PyTorch, JAX, TensorFlow, or an equivalent, including developing custom models, loss functions, data pipelines, training loops, and inference workflows.
You understand common machine learning model families, including neural network architectures, and can select or adapt approaches based on data availability, computational constraints, mission requirements, and operational risk.
You have experience developing reproducible, end-to-end ML workflows, including data validation, experiment tracking, model and data versioning, integration testing, and model evaluation.
You have working knowledge of at least one aerospace domain, such as astrodynamics, spacecraft systems, navigation, mission design, or flight and ground software, or the ability to rapidly build expertise in these areas.
You are familiar with machine learning applications for physical or engineered systems, reinforcement learning, or decision-making methods.
You can effectively communicate complex technical concepts and collaborate with multidisciplinary engineering teams.
You take ownership of your work, approach challenges with curiosity, and are comfortable navigating technical ambiguity.

Nice To Haves

An M.S. in Aerospace Engineering, Computer Science, Artificial Intelligence, Robotics, or a related field.
Applying model-based or model-free reinforcement learning, model predictive control (MPC), Markov decision processes (MDPs), partially observable Markov decision processes (POMDPs), or hybrid planning approaches to physical systems.
Developing autonomy architectures spanning perception, estimation and navigation, planning and scheduling, control, and fault management.
Building simulation or digital-twin environments for model development, evaluation, and sim-to-real transfer.
Integrating ML-enabled capabilities into guidance, navigation, and control (GN&C), mission design, navigation, flight software, or systems-engineering workflows.
Applying optimization, probability, statistics, and rigorous experimental design to complex engineering problems.
Using probabilistic modeling or Bayesian inference to address engineering challenges.
Communicating complex technical concepts across machine learning, navigation, mission design, flight software, operations, and systems engineering.
Using agentic AI tools to support engineering workflows while maintaining technical accuracy, security, and reproducibility.

Responsibilities

Develop machine learning solutions for complex engineering challenges.
Translate mission, operations, and engineering needs into well-defined ML and data-driven problems. Establish success metrics, baselines, datasets, evaluation plans, and quantitative acceptance criteria to develop solutions that address real-world mission requirements.
Design and implement ML-enabled capabilities.
Select, develop, evaluate, and maintain machine learning solutions that support spacecraft mission planning, operations, autonomy, navigation, physical-system modeling, signal extraction, and internal engineering workflows. Apply appropriate methods based on mission needs, data availability, computational constraints, and operational requirements.
Own technically complex projects from concept to deployment.
Take ownership of technical work packages from initial problem formulation through implementation, integration, documentation, and operational handoff. Define technical approaches, assess trade-offs, identify risks, and communicate architectural decisions and recommendations to stakeholders.
Build reliable and reproducible ML workflows.
Develop and maintain end-to-end machine learning workflows, including data curation and validation, experiment tracking, model and data versioning, configuration management, automated regression testing, and performance monitoring. Apply modern software engineering practices to ensure solutions are maintainable, scalable, and reliable.
Evaluate model performance and validate results.
Design rigorous evaluation strategies and domain-appropriate metrics to assess nominal, edge-case, and off-nominal performance. Identify data leakage, distribution shifts, and other factors that could impact model reliability. Use quantitative analysis and experimentation to validate model performance and inform technical decisions.
Integrate ML capabilities into aerospace systems.
Collaborate with navigation, mission design, flight software, systems engineering, and operations teams to integrate machine learning solutions into broader engineering architectures and workflows. Ensure ML capabilities align with mission requirements, system constraints, and operational needs.
Research and apply emerging technologies.
Read, synthesize, and apply relevant technical literature, emerging research, and innovative methodologies in machine learning, optimization, and autonomy. Evaluate new approaches and identify opportunities to advance Advanced Space's technical capabilities.
Communicate technical findings and recommendations.
Document technical approaches, assumptions, results, limitations, and recommendations. Present findings through design reviews, technical documentation, and stakeholder discussions, translating complex ML concepts into clear, actionable insights for multidisciplinary teams.
Leverage modern AI-assisted engineering tools.
Use company-approved AI-assisted and agentic engineering tools responsibly to support software development, documentation, research, and analysis. Critically evaluate generated outputs and apply appropriate security, source-provenance, reproducibility, and technical-validation practices.