This job posting is inactive.
To view more jobs from this company, please visit their other roles at:
Plusai Roles

Software Engineer Intern - ML Simulation

Plusai (View all Jobs)

Santa Clara, CA

Programming Languages Mentioned

Python

We’re seeking an enthusiastic and driven Simulation/ML Engineer Intern to join our team and work on an exciting project that blends Large Language Models (LLMs) with simulation technology. In this role, you’ll help develop a tool that can generate realistic, scalable simulation scenarios from text and real road data. This is a fantastic opportunity to apply your machine learning and robotics knowledge to real-world challenges, while working on a project that will revolutionize how simulation scenarios are created, with minimal manual effort. You’ll be at the forefront of innovation, helping us expand our capabilities in testing autonomous vehicles using large-scale simulation with LLM-driven solutions.

Responsibilities:

Gain a strong understanding of our simulation systems and data infrastructure

Develop machine learning models to generate realistic simulation scenarios from text, images and other types of recorded data

Collaborate with the simulation teams to refine and optimize the generated scenarios

Test and improve model performance based on ground truth data

Contribute to integrating the tool into existing simulation workflows

Required Skills:

Currently pursuing or recently graduated with a degree in Computer Science, Robotics, Machine Learning, AI, or a related field

1+ years of experience in machine learning (Deep Learning, NLP, etc.)

Experience with simulation frameworks (e.g., Gazebo, V-REP, Unity) and robotics applications

Strong programming skills in Python and familiarity with machine learning libraries (TensorFlow, PyTorch, etc.)

Preferred Skills:

Experience working with Large Language Models (LLMs) and multimodal learning (text + images)

Familiarity with scenario generation and counterfactual simulation techniques

Knowledge of text-to-image generation and data preparation for machine learning in simulation environments