Research Engineer Internship

About Avride

Avride is a US-based developer of autonomous vehicles and delivery robots. We develop and operate both autonomous cars and delivery robots that share technologies and mutually benefit from each other's advancements—a unique approach in the industry. 

About the Internship

At Avride, Research Engineer Interns operate at the intersection of cutting-edge academic research and real-world engineering. You will use our massive datasets of real driving logs to train models and develop algorithms.

During this internship, you will be embedded in the ML Prediction and Planning team, which is responsible for building machine learning models that enable autonomous vehicles to understand their environment and make safe, efficient driving decisions on real roads. The team focuses on predicting the behavior of surrounding agents and generating trajectories that the vehicle can follow in complex, dynamic scenarios.

You will be paired with a dedicated senior researcher and work on problems directly impacting real-world driving performance. This program is designed to give you a deep understanding of how to take a theoretical concept from a research paper, prototype it, and evaluate its performance in a complex, safety-critical system.

What You’ll Do

We are currently offering two different internships within our ML Prediction and Planning team for the Summer of 2026. 

Autonomous Vehicles

• Applied Research Project: Take ownership of a research project focused on exploring how model ensembling strategies influence the gap between open-loop (training) and closed-loop (simulation) performance. You will review relevant literature, formulate hypotheses, and prototype solutions using Python and ML frameworks (like PyTorch).
• Design Ensembling Strategies: Implement and evaluate multiple ensembling approaches, including blending models trained with different random seeds, combining checkpoints from different training stages, and applying weighted averaging or learned blending of model outputs.
• Run Controlled Experiments: Systematically compare single-model vs ensemble performance and seed diversity vs checkpoint diversity, and measure their impact on open-loop metrics (training/validation loss, accuracy) and closed-loop metrics (simulation performance, safety, stability).
• Analyze Metric Alignment: Investigate the correlation (or lack thereof) between open-loop and closed-loop improvements, identify cases where ensembling improves one metric but degrades the other, and formulate hypotheses explaining the observed behavior.

Simulation

• Applied Research Project: You will work on evaluating and improving the behavior of ML-driven traffic agents in our autonomous driving simulator. Our prediction model generates multiple trajectory candidates for each simulated agent at every step. Your job is to design evaluation functions that select trajectories with desired properties — from realistic to adversarial — and build quantitative metrics to measure how agent behavior changes. Today we assess realism visually; you will replace that with data-driven evaluation that becomes the standard tool for measuring every future improvement to our agent simulation. You'll work with real driving data, run experiments on large scenario pools, and produce results that directly influence the team's roadmap for agent simulation.
• Design and implement algorithms: work alongside your mentor to design, test, and iterate algorithms that select agent trajectories optimizing for different objectives: aggressiveness, interaction density, route fidelity.
• Build evaluation metrics: for comparing agent behavior strategies: interaction intensity (time-to-collision, proximity), kinematics plausibility (acceleration, jerk), and distributional similarity to real traffic.
• Data-Driven Experimentation: run experiments on large-scale scenario pools, comparing ML agents agains baseline approaches and measuring the impact of different strategies.
• Work with production codebase: the prediction models you'll experiment with are the same ones deployed in our autonomous vehicles. Your work is a part of a C++ simulation pipeline running large-scale scenario evaluation.
• Knowledge Sharing: Conclude your internship by presenting your methodology, experimental results, and data-driven recommendations on where trajectory ranking is sufficient and where model-level changes are required.

What You’ll Need

• Education: Currently pursuing a Master’s or PhD (highly preferred) in Computer Science, Robotics, Machine Learning, Applied Mathematics, or a related field with an expected graduation date between Winter 2026 and Spring 2027. 
• Machine Learning / Math Foundation: Strong understanding of deep learning, reinforcement learning, computer vision, optimization, or probabilistic modeling.
• Programming Skills: Proficiency in Python and deep learning frameworks (PyTorch, TensorFlow). Basic familiarity or willingness to learn C++.
• Research Acumen: Ability to read, understand, and implement algorithms from academic research papers. A strong analytical mindset for designing experiments and interpreting data.
• Eagerness to Learn: Highly collaborative, open to feedback, and excited to tackle unsolved problems in the autonomous driving space.

What You’ll Get

• 1:1 Mentorship: Direct guidance from leading researchers and engineers in the autonomous vehicle industry to help you navigate technical roadblocks and grow your career.
• Massive Compute & Data: Access to state-of-the-art driving data to fuel your experiments.
• Networking & Culture: Invitations to tech talks, paper reading groups, intern social events, and cross-team collaborations.