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 Bachelor's, 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.

Please note that this is an in-person internship based at our office in Austin, Texas.  We are prioritizing candidates who currently reside within commuting distance of Austin.  We do not provide relocation assistance, travel reimbursement, or housing stipends for this position.

About the Team

AVRIDE is an autonomous driving company with the mission to make transportation safer and more efficient through cutting-edge technology. We hold a unique position in the market, developing self-driving taxis and delivery robots. Our delivery robot division already has production in the US and Japan. Our team consists of highly talented engineers with extensive expertise. Joining us means diving into a startup atmosphere and making a significant impact on the company's results and the autonomous industry as a whole.

About the Role

As a Senior Software Developer at Avride, you’ll lead the development of trajectory planning algorithms for autonomous vehicles, ensuring smooth system integration and real-world performance. You'll work across teams, drive technical decisions, and help build safe, intelligent driving behavior.

What You'll Do

• Design, develop and verify detailed algorithms related to autonomous vehicle trajectory geometry and all related components.
• Analyze autonomous rover behavior to detect inconsistencies and implement solutions, ensuring seamless operation across various system components.
• Overseeing the contributions to the geometry planning component of subordinate software engineers.
• Collaborate with other teams, responsible for various system modules related to trajectory geometry, ensuring their synchronized and cohesive operation.
• Ensure that data flow and commands are appropriately coordinated between these components for smooth and efficient operation of the autonomous vehicle.
• Devise and implement metrics for autonomous vehicle evaluation.
• Devise and implement feedback mechanisms about autonomous vehicle behavior.
• Simulating a variety of driving scenarios, ensuring the metrics remain comprehensive and cover an expansive range of potential situations.
• Quality Assurance Team feedback analysis.
• Ability to isolate issues within intricate, multi-component systems and conduct thorough root cause analysis.
•  Proficient code review.

What You'll Need

• Educational Requirement: A bachelor's degree in computer science, engineering or mathematics, or their equivalents.
• At least 12 years of experience as a software engineer.
• At least 5 years of experience with Linux and Docker.
• At least 3 years of relevant work experience in IT.
• Proven ability to implements leading AI related solutions.
• Strong knowledge of such programming languages as C++, Python.
• Proven understanding of basic ML models and its applications; Ability to implement and validate basic ML models.
• Should possess the confidence to guide teams and management towards making decisions; prepared to assertively seek information and responses.
• Proven ability to work with Kubernetes and AWS.
• Solid understanding of the software development lifecycle.
• Proven ability to work with members of cross-functional teams.
• Strong knowledge of wide range of algorithms to build performance efficient systems, proficiency with writing complex algorithmic logic.
• Excellent communication and interpersonal skills.
• Good critical thinking and problem-solving skills.
• Knowledge of traffic laws and driving norms to ensure the vehicle adheres to legal and safety standards.

About the Team

Our team develops the core software and data processing systems that power motion planning and decision-making in autonomous vehicles. We work at the intersection of machine learning, large-scale data infrastructure, and real-time vehicle control, collaborating across engineering, analytics, and product teams to deliver safe and intelligent driving capabilities.

About the Role

We are looking for a creative & driven Machine Learning Engineer to join our autonomous vehicle team. You will be at the center of our efforts to build intelligent systems that can understand, predict, and safely navigate a complex and dynamic world. This role involves designing and training the next generation of deep learning models that form the brain of our vehicle, learning from petabytes of real-world driving data. If you are passionate about applying cutting-edge ML to solve high-stakes robotics challenges, we want to hear from you.

What You'll Do

• Design, train, and deploy state-of-the-art machine learning models for behavioral prediction and motion planning
• Develop robust data pipelines to process, clean, and label massive-scale vehicle sensor and simulation datasets
• Work with deep learning architectures such as transformers to model complex temporal interactions between traffic agents
• Establish and own the metrics for model performance, and create evaluation frameworks that correlate with on-road safety and performance
• Collaborate with software engineers to integrate and optimize trained models for real-time inference on the vehicles embedded hardware
• Stay current with the latest research in machine learning, imitation learning, and reinforcement learning, and apply novel techniques to our systems

What You'll Need

• Strong proficiency in Python and hands-on experience with modern deep learning frameworks (e.g., PyTorch, TensorFlow, or JAX)
• Solid understanding of machine learning fundamentals, including various neural network architectures, training methodologies, and evaluation techniques
• Experience with the full machine learning lifecycle, from data exploration and prototyping to deployment and monitoring
• Proficiency in C++ for writing high-performance model inference code

Nice to Have

• A strong track record in ML competitions (e.g., Kaggle) or contributions to major open-source ML projects
• Experience applying ML to problems in robotics, such as behavioral prediction, motion planning, or computer vision
• Experience with MLOps tools and platforms (e.g., MLflow, Kubeflow, Weights & Biases)
• Experience with large-scale distributed data processing and training frameworks (e.g., Spark, Ray)
• Publications in top-tier ML or robotics conferences (e.g., NeurIPS, ICML, CVPR, ICLR, CoRL, RSS)

About the Team

Our team develops the core software and data processing systems that power motion planning and decision-making in autonomous vehicles. We work at the intersection of machine learning, large-scale data infrastructure, and real-time vehicle control, collaborating across engineering, analytics, and product teams to deliver safe and intelligent driving capabilities.

About the Role

We are seeking a highly skilled C++ Software Engineer to join our core Motion Planning team. You will be at the forefront of developing the decision-making logic that enables our autonomous vehicles to navigate the complexities of the real world safely and efficiently. If you have a passion for solving hard algorithmic problems and writing high-performance code, this is the perfect opportunity for you.

What You'll Do

• Design, implement, and optimize cutting-edge motion planning algorithms in modern C++ (C++17/20)
• Develop robust solutions for trajectory generation, pathfinding, and behavioral decision-making in dynamic environments
• Analyze and debug system performance using simulation, log playback, and on-vehicle testing data
• Collaborate closely with engineers from Perception, Prediction, and Control teams to build a cohesive and reliable self-driving system
• Write clean, maintainable, and optimized production-quality code
• Profile and optimize algorithms to meet real-time performance constraints

What You'll Need

• Exceptional proficiency in modern C++ and a deep understanding of object-oriented design principles
• Strong foundational knowledge of algorithms and data structures, particularly those relevant to robotics (e.g., graph search, computational geometry, optimization techniques)
• Experience with software development tools and practices, including Git, CI/CD, and code reviews

Nice to Have

• Proven success in competitive programming contests such as Google Code Jam, Hash Code, Topcoder Open, ICPC, or similar events
• Professional or academic experience in robotics, specifically with motion planning
• Experience with performance-critical software development, including multi-threading and memory optimization
• Knowledge of machine learning techniques (e.g., reinforcement learning, imitation learning) applied to planning or decision-making problems
• Solid mathematical background, including linear algebra and probability theory
• Knowledge of GPU programming (e.g., CUDA, OpenCL) for accelerating algorithms