Autonomy Engineer Intern, Reinforcement Learning, 2027 (HQ)

Location: San Mateo, California, United States; onsite internship.

Compensation: $47/hour for undergraduate students, $53/hour for master's students, and $70/hour for PhD students.

Company

hirify.global develops autonomous drones and flight technologies for inspection, public safety, defense, cinematography, and other operational use cases.

What you will do

• Develop and deploy reinforcement-learning and related policy-learning methods for autonomous drone planning, navigation, and control.
• Train policies for obstacle avoidance, dynamic goal-seeking, learned cost shaping, value functions, and trajectory optimization in complex 3D environments.
• Build scalable datasets and training loops using Isaac Lab, domain randomization, residual learning, and safety filters, then validate results on real drones.
• Develop human-in-the-loop shared-control policies that combine pilot intent, autonomy priors, and uncertainty-aware behaviors.
• Explore decentralized multi-agent coordination for coverage, pursuit, and collaborative mapping with minimal communications.
• Collaborate with perception, mapping, controls, and product teams to move research from simulation into field operations.

Requirements

• Current PhD student in Robotics, Machine Learning, Controls, or a related field.
• Strong fundamentals in reinforcement learning and control theory, with comfort working with safety and robustness concepts.
• Proficiency in Python and PyTorch, JAX, or Ray RLlib, plus proficiency in at least one of C++ or CUDA.
• Hands-on experience with robotics simulation using Isaac Lab, MuJoCo, or PyBullet and with sim-to-real techniques.
• Experience training and deploying policies for navigation, manipulation, or locomotion on real robots or autonomous vehicles.

Nice to have

• Publications at CoRL, ICRA, IROS, RSS, or NeurIPS.
• Experience optimizing onboard inference with TensorRT, quantization, or sparsity.
• Familiarity with policy-learning methods beyond vanilla reinforcement learning, including diffusion policies, imitation learning/behavioral cloning, offline reinforcement learning, or model-based reinforcement learning.
• Experience with multi-agent reinforcement learning or distributed training.

Culture & Benefits

• Research is tested on production-ready aircraft and edge compute, with real-drone flight testing on a weekly basis.
• Safety-focused development combines reinforcement learning with formal constraints, uncertainty estimation, and conservative action filters.
• Multidisciplinary collaboration across perception, mapping, controls, product, and field-operations functions.
• Full-time employees may enroll in benefit plans and access incentives and stipends.
• Inclusive environment focused on diverse perspectives and collaboration.