Senior Autonomy Machine Learning Engineer

Job Description

Job Description

Are you passionate about shaping the future of humanity's presence in space? Lunar Outpost, a trailblazer in space robotics, invites you to join our team ! Lunar Outpost is dedicated to creating a sustainable presence in space, while also driving positive impacts here on Earth. We are seeking a talented  Senior Autonomy Machine Learning Engineer . As a Senior Autonomy Machine Learning Engineer, you will research, develop, train, evaluate, and deploy machine learning models for Lunar Outpost’s lunar rovers, command-and-control platforms, terrestrial robotic systems, and orbital assets. Working at the intersection of robotics, autonomy, AI, and space exploration, you will develop technologies that enable robotic systems to perceive their environment, interpret operator intent, reason about mission objectives, generate plans, and safely execute complex tasks with reduced operator oversight. Your work will include transformer-based architectures, vision-language models, multimodal foundation models, robot learning, and intelligent planning and decision-support systems. You will help build datasets, evaluation frameworks, software infrastructure, and deployment pipelines that support applications ranging from natural-language vehicle control to onboard reasoning, anomaly detection, mission summarization, and multi-robot supervision. You will collaborate closely with robotics, software, simulation, and command-and-control engineering teams to transition emerging AI research into reliable capabilities.

 

Take the #NextLeap with Lunar Outpost and work on the Pegasus LTV, which will carry NASA astronauts farther than they've ever been before on the lunar surface!

Working Conditions / Schedule: This position is required to be onsite Monday, Tuesday, Thursday, and Friday from 9:00 a.m. to 5:00 p.m. Where applicable, employees may work remotely on Wednesdays from 9:00 a.m. to 5:00 p.m. Additional hours may be required based on business needs.

Key Responsibilities:

• Research, design, train, fine-tune, and evaluate transformer-based machine learning architectures for autonomous robotic and command-and-control applications

• Develop vision-language-action models, vision-language models, and other multimodal models that connect operator intent and sensor observations to robot plans and actions

• Build capabilities for natural-language command interpretation, task decomposition, mission planning, action generation, operator decision support, and autonomous task execution

• Develop human-robot teaming capabilities that enable operators to efficiently supervise and command multiple robotic assets

• Create systems for mission summarization, anomaly detection, situational awareness, course-of-action generation, and operator-reviewable recommendations

• Integrate machine learning models with robotic platforms, simulation environments, command-and-control software, and autonomy frameworks

• Conduct hardware-in-the-loop tests, field tests, and structured demonstrations to validate capabilities under realistic operating conditions

• Participate in design reviews, trade studies, technical risk assessments, test-readiness reviews, and demonstrations

Required Qualifications:

• Bachelor’s degree in Computer Science, Machine Learning, Artificial Intelligence, Robotics, Electrical Engineering, Computer Engineering, Aerospace Engineering, or a related technical field, or equivalent practical experience

• 3 to 5 years of relevant professional, academic, or research experience developing machine learning systems, autonomous systems, or intelligent robotic applications

• Experience developing and evaluating deep learning models using Python and a modern machine learning framework such as PyTorch, JAX, or TensorFlow

• Experience in at least one of the following areas:

• • Vision-language models or multimodal foundation models

• • Robot learning, imitation learning, or reinforcement learning

• • Natural-language planning, tool use, or agentic systems

• • Autonomous planning, reasoning, or task execution

• Experience preparing datasets, implementing training pipelines, defining evaluation metrics, and analyzing model performance
• Strong software engineering skills, including experience writing maintainable and testable software
• Experience with Linux-based development environments, Git, and collaborative software development workflows 
• Ability to translate research concepts into working prototypes and evaluate those prototypes against measurable system objectives
• Ability to communicate complex technical concepts, experimental results, limitations, and risks to multidisciplinary teams
• Comfortable working in a research-oriented, agile, and interdisciplinary environment where requirements and technical approaches may evolve rapidly
• U.S. Person

Preferred Qualifications:

• Master’s degree or Ph.D. in Machine Learning, Artificial Intelligence, Robotics, Computer Science, or a related field
• Experience developing or fine-tuning VLMs, VLAs, large language models, or multimodal transformer architectures
• Experience with robot foundation models, action tokenization, multimodal policy learning, hierarchical policies, or language-conditioned control
  
• Experience applying supervised fine-tuning, parameter-efficient fine-tuning, preference optimization, imitation learning, or reinforcement learning to foundation models
  
• Experience with robotics middleware and autonomy frameworks such as ROS2
• Experience integrating learned models with robot perception, planning, control, or command-and-control systems
• A record of technical innovation demonstrated through deployed systems, open-source contributions, publications, patents, or significant project achievements
  

Compensation & Benefits: Compensation level and base salary are competitively structured and thoughtfully determined based on factors such as relevant skills, experience, education, and the scope of the role.

• Comprehensive health coverage: Medical, dental, and vision benefits, with 70% of premiums covered by the employer
• Paid time off: Three (3) weeks per year of vacation
• Retirement plan: Up to 4% employer match on 401(k) contributions
• Paid holidays: 11 company-recognized holidays
• Parental leave
• Educational reimbursement opportunities to support company objectives, continued learning, and career development

Lunar Outpost Inc. is an equal opportunity employer. Lunar Outpost Inc. does not discriminate on the basis of race, color, religion, sex (including pregnancy, sexual orientation, and gender identity), national origin, ethnicity, age, disability, veteran status, genetic information, or any other characteristic protected by applicable law. All employees, including executives and human resources personnel, are expected to conduct themselves with professionalism and treat others with dignity and respect in accordance with this policy.