Post Doctoral Researcher

Howard University • Washington, DC

11d • $75,000 - $85,000

About The Position

on real-time task rescheduling for Earth observation missions. The postdoctoral researcher will lead the design, implementation, and evaluation of multi-agent reinforcement learning (MARL) algorithms that enable satellites to cooperatively adapt to disruptions such as communication blackouts, satellite failures, and dynamic observation demands. This role supports the broader mission of building scalable, resilient space systems capable of operating with minimal human intervention in contested and resource-constrained environments. The postdoctoral researcher will contribute to a federally funded research initiative focused on building the next generation of intelligent, resilient Earth observation satellite systems. The position involves full lifecycle development of a decentralized autonomy framework, from theoretical design to high-fidelity simulation and performance analysis. The successful candidate will operate at the intersection of aerospace engineering, artificial intelligence, and distributed systems, contributing both as an independent researcher and as part of a collaborative academic team. This role requires a high degree of innovation, systems-level thinking, and the ability to translate theoretical advancements in multi-agent reinforcement learning into practical solutions for dynamic, resource-constrained space environments. The postdoc will also have the opportunity to shape future project directions, mentor junior team members, and co-author publications for top-tier conferences and journals.

Requirements

• U.S. citizenship is required due to federal export control and security compliance requirements"
• Ph.D. in Aerospace Engineering, Space Sciences, Computer Science, Robotics, or a closely related field.
• Familiarity with reinforcement learning, multi-agent systems, or autonomous decision making.
• Experience with space mission modeling, orbital mechanics, or spacecraft subsystems.
• Proficiency in Python, with experience in simulation tools such as Basilisk, STK, GMAT, or equivalent.
• Familiarity with AI frameworks such as PyTorch, OpenAI Gymnasium, etc.
• Excellent written and verbal communication skills and a record of research publications.

Responsibilities

• Design and implement multi-agent reinforcement learning (MARL) algorithms for dynamic task allocation and coordination within LEO satellite constellations
• Simulate satellite behavior under partial failures, communication blackouts, and mission disruptions
• Develop and evaluate candidate reward functions that balance competing mission objectives (e.g., task priority, power consumption, latency)
• Integrate peer-to-peer communication protocols and ground-station feedback loops into the autonomy framework
• Analyze performance through Pareto optimization, sensitivity studies, and robustness evaluations
• Collaborate with interdisciplinary teams and contribute to peer-reviewed publications

Benefits

• Comprehensive medical, dental, and vision insurance, plus mental health support
• PTO, paid holidays, flexible work arrangements
• Competitive salary, 403(b) with company match
• Ongoing training, tuition reimbursement, and career advancement paths
• Wellness programs, commuter benefits, and a vibrant company culture

What This Job Offers

• Job Type: Full-time
• Education Level: Ph.D. or professional degree