Machine Learning Engineer

In Orbit Aerospace is building the next generation of autonomous systems. Our work bridges the development of vehicles that operate in the air, space, and everywhere in between with edge-resident AI/ML for secure, reliable autonomy.

Machine Learning Engineer

As a Machine Learning Engineer, you will develop software that brings machine learning and intelligent autonomy capabilities into spacecraft systems. You will work across software development, machine learning, spacecraft telemetry, and system integration to turn algorithms and prototypes into reliable operational capabilities.

You will report to the Lead ML Engineer and collaborate closely with software, GNC, systems, and hardware engineers. This role is primarily a software engineering position and requires strong programming and problem-solving skills, along with practical experience in machine learning, data science, or AI. Experience with embedded or flight systems is valuable but not required.

Responsibilities

• Design, develop, test, and maintain software in C/C++ and Python supporting spacecraft autonomy, telemetry processing, health monitoring, and intelligent decision support.
• Translate ML and data-science prototypes into maintainable, testable, production-quality software.
• Develop and integrate interfaces between algorithms, applications, sensors, hardware, and other system components using common communication protocols and data formats.
• Develop modular software with well-defined interfaces, unit and integration testing, and Git-based collaborative development workflows.
• Debug and troubleshoot software across application, operating-system, communication, and hardware-interface boundaries.
• Develop and integrate ML inference pipelines, including data preprocessing, model execution, post-processing, and communication of model outputs.
• Develop and evaluate ML approaches for problems such as anomaly detection, classification, regression, time-series analysis, and multi-sensor data analysis.
• Support deployment and optimization of software and ML capabilities for resource-constrained computing environments.
• Collaborate with domain experts to integrate spacecraft telemetry, GNC outputs, fault-management concepts, and other mission data into ML-enabled applications.
• Contribute to AI-enabled operator tools, including telemetry analysis, fault reasoning, retrieval-based systems, and natural-language interfaces.

Basic Qualifications

• Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, Aerospace Engineering, or a related technical field.
• 2+ years of software development experience.
• Strong programming skills in C/C++ and Python.
• Strong understanding of software-engineering fundamentals, including data structures, algorithms, software architecture, interfaces, debugging, and testing.
• Experience developing software that communicates across components, processes, devices, or networked systems using common interfaces and protocols.
• Experience developing software in Linux or similar environments and using Git-based collaborative development workflows.
• Practical experience with machine learning, data science, or AI involving development or technical implementation beyond simply consuming commercial generative-AI APIs.
• Understanding of fundamental ML concepts including data preprocessing, training and validation, model evaluation, performance metrics, and generalization.
• Ability to independently investigate complex technical problems and work effectively across software and engineering disciplines.

Preferred Experience and Skills

• Experience developing software for embedded, real-time, aerospace, spacecraft, robotics, automotive, or other hardware-integrated systems.
• Familiarity with embedded computing concepts, hardware/software integration, resource constraints, concurrency, or real-time considerations.
• Experience with communication technologies and protocols such as TCP/UDP, serial, CAN, SPI, I2C, or similar interfaces.
• Experience with spacecraft flight-software frameworks, telemetry architectures, or standards such as cFS, F′, or CCSDS.
• Experience with machine-learning techniques such as anomaly detection, classification, regression, ensemble methods, time-series analysis, or multi-sensor data.
• Experience deploying ML models using frameworks and inference technologies such as PyTorch, TensorFlow, ONNX, TensorRT, or equivalent.
• Experience with model optimization, quantization, compression, hardware-accelerated inference, or other resource-constrained ML deployment techniques.
• Familiarity with spacecraft GNC, state estimation, fault detection and isolation, or autonomous systems.
• Experience with simulation, software-in-the-loop, hardware-in-the-loop, or system-level testing.
• Experience developing AI systems beyond basic API integration, such as retrieval-augmented generation, local model inference, model evaluation, fine-tuning, tool/function calling, or agentic systems.

ITAR Requirements: To conform to U.S. Government space technology export regulations, including the International Traffic in Arms Regulations (ITAR) you must be a U.S. citizen, lawful permanent resident of the U.S., protected individual as defined by 8 U.S.C. 1324b(a)(3), or eligible to obtain the required authorizations from the U.S. Department of State.