Engineer I, VLA Planning and Control Deployment (Intern)

CARIAD, Inc.•Mountain View, CA

21h•$45 - $69•Onsite

About The Position

The Engineer I, VLA Planning and Control Deployment (Intern) will improve planning and control algorithms used in CARIAD Inc.’s autonomous-driving deployment stack. Working with planning and deployment engineers, the intern will apply operations research and classical control methods to improve trajectory feasibility, smoothness, and computational reliability. The work focuses on constrained optimization, trajectory refinement, controller performance, and integration of learned model outputs with executable vehicle behavior. The intern will prototype, train, and fine-tune VLA models or supporting perception and world-model components; investigate recent methods and conduct a focused research project with mentor guidance; prepare driving datasets and evaluation splits; run controlled experiments and ablations; and evaluate model accuracy, driving behavior, robustness, and inference cost. The role also involves analyzing offline and simulation failures, collaborating on model interfaces, documenting methods and results, reviewing code, presenting findings, and delivering a reproducible prototype and final technical report. This is an on-site, hourly W-2 internship based in Mountain View, California. The candidate must be local, and relocation is not available. Immediate availability is required, with a prompt start after offer acceptance and successful completion of background and drug screening. The internship schedule is to be determined.

Requirements

Foundations in numerical optimization, linear algebra, and dynamical systems.
Hands-on experience with quadratic programming or classical control methods such as MPC, LQR, or PID.
Ability to implement and debug algorithms in Python or C++ and contribute to deployment code.
Ability to assess trajectory feasibility, tracking error, constraint violations, and runtime.
Coursework, research, or project experience in optimization, motion planning, or control; prior industry experience is not required.
Pursuing a degree in Operations Research, Control Engineering, Robotics, Electrical Engineering, Applied Mathematics, or a related field.
Must be local to Mountain View, California; relocation is not available.
Immediate availability is required.

Nice To Haves

Experience formulating QPs with OSQP, qpOASES, or HPIPM.
Knowledge of MPC, trajectory optimization, vehicle dynamics, and lateral or longitudinal control.
Experience with C++, profiling, sparse numerical methods, solver warm starts, or embedded deployment.
Experience with simulation, log replay, software-in-the-loop, or hardware-in-the-loop validation.
Master’s or PhD study emphasizing operations research, optimization, control theory, or vehicle dynamics.

Responsibilities

Prototype, train, and fine-tune VLA models or supporting perception and world-model components.
Investigate recent methods and implement a focused research project with mentor guidance.
Prepare driving datasets and evaluation splits, and improve data quality and coverage.
Run controlled experiments and ablations, maintaining reproducible configurations and experiment records.
Measure model accuracy, driving behavior, robustness, and inference cost.
Analyze failures in offline and simulation evaluation and collaborate with planning and deployment engineers on model interfaces.
Document methods, results, and limitations; review code; and present findings.
Deliver a reproducible prototype and a final technical report.
Apply optimization and classical control methods to improve trajectory feasibility, smoothness, and computational reliability.