Autonomy Software Engineering Internship, World Modeling
Persona AI Inc2 months ago
Houston, TX, USAIntern
Responsibilities
- Design and implement autonomy and behavior-coordination algorithms for an industrial humanoid platform.
- Integrate manipulation, locomotion, and perception skills into autonomous robot behaviors with robotics engineers.
- Implement data-curation pipelines for understanding real-world industrial tasks.
- Develop synthetic-data generation pipelines for post-training humanoid world models.
- Build pipelines for autonomous-behavior evaluation, benchmarking, and regression testing.
- Convert raw industrial video footage from shipyards, steel fabrication, and welding cells into structured, high-quality training data.
- Design and evaluate reasoning benchmarks measuring how well fine-tuned world models ground language queries in industrial scenes.
- Work with the autonomy team alongside machine-learning, perception, and simulation engineers.
Requirements
- Currently pursuing a BS, MS, or PhD in Robotics, Computer Science, Machine Learning, Electrical Engineering, or a related field; recent graduates are also welcome.
- Hands-on experience training, fine-tuning, or evaluating modern deep-learning models in PyTorch.
- Strong Python skills for data-processing scripts, training loops, and evaluation harnesses.
- Working familiarity with at least one vision-language model, large language model, or video-understanding model.
- Practical experience building data pipelines involving ingestion, filtering, labeling workflows, deduplication, and train/validation/test splits.
- Comfort working in Linux with Git, Docker containers, and cloud GPU infrastructure.
- Ability to make steady progress on an open-ended research problem with weekly check-ins rather than daily direction.
- Direct experience with NVIDIA Cosmos or comparable world foundation models is preferred.
- Exposure to NVIDIA Isaac Sim, Omniverse, or OpenUSD for synthetic-data generation and scene variability is preferred.
- Familiarity with humanoid or mobile-manipulator robotics, ROS, ROS 2, and autonomy stacks is preferred.
- Experience with motion-capture data, egocentric video capture, or first-person dataset construction is preferred.
- Exposure to behavior trees, task and motion planning, or LLM-driven planning architectures is preferred.
- Familiarity with NVIDIA Isaac Lab, NIM microservices, or the Hugging Face training ecosystem is preferred.
- Prior internship, research, or open-source work involving physical AI, embodied reasoning, or robot learning is preferred.
Benefits
- Paid summer internship in Houston, TX, working onsite.
- Flexible work environment and meaningful technical mentorship.
- Access to advanced prototyping tools and labs, with freedom to experiment and innovate.
- Inclusive team committed to diversity and equal opportunity.