UTern

Opportunities · Internship

Intern, Model Integration

HARMAN · Shanghai, China

Applies on Workday≈$10-$20/hr

Role overview

What you'll own

  • You will work with platform-specific inference frameworks and toolchains to improve model compatibility, efficiency, and runtime performance.
  • Analyze performance bottlenecks, troubleshoot model compatibility and runtime issues, and propose practical optimization solutions.
  • Build reusable scripts, test cases, benchmarks, and technical documentation for model deployment and performance evaluation.
  • Collaborate with algorithms, platform, and integration engineers to support model delivery and customer demonstration activities.

Requirements and eligibility

  • Currently pursuing a Bachelor’s or master’s degree in computer science, Artificial Intelligence, Electronic Engineering, Automation, Automotive Engineering, or a related field.
  • Available at least 3 days per week for a minimum internship period of 3 months.
  • Ability to design reproducible performance tests, analyze results, and clearly document technical findings.
  • Strong interest in emerging AI acceleration technologies and the ability to quickly learn new hardware and software toolchains.

Preferred, not required

  • if You Have
  • Project, research, competition, or internship experience in model deployment, edge AI, embedded AI, or heterogeneous computing.
  • Experience with NVIDIA Jetson, Qualcomm Snapdragon platforms, Samsung Exynos, or other embedded accelerators.

Dates for this one

Only the dates this listing publishes. Anything it leaves out is left out here too.

Posted

Sep 16, 2026

The employer's own record

Usually listed

Checking opening history…

Filed pay record

Checking public pay records…

Read the full listing context

A Career at HARMAN As a technology leader that is rapidly on the move, HARMAN is filled with people who are focused on making life better. Innovation, inclusivity and teamwork are a part of our DNA.

When you add that to the challenges we take on and solve together, you’ll discover that at HARMAN you can grow, make a difference and be proud of the work you do every day.

A Career at HARMAN Automotive We’re a global, multi-disciplinary team that’s putting the innovative power of technology to work and transforming tomorrow.

At HARMAN Automotive, we give you the keys to fast-track your career. • Engineer audio systems and integrated technology platforms that augment the driving experience • Combine ingenuity, in-depth research, and a spirit of collaboration with design and engineering excellence • Advance in-vehicle infotainment, safety, efficiency, and enjoyment What You’ll Be Part Of This internship focuses on deploying, optimizing, and evaluating AI/ML models across heterogeneous embedded and edge-computing platforms, including NVIDIA Jetson, Qualcomm, and Samsung Exynos.

You will work with platform-specific inference frameworks and toolchains to improve model compatibility, efficiency, and runtime performance. How You’ll Make An Impact • Integrate and deploy AI/ML models on different target platforms, including NVIDIA Jetson, Qualcomm, and Samsung Exynos.

• Convert and adapt models for platform-specific inference engines and deployment toolchains. • Optimize and quantize models according to target hardware constraints and performance requirements, including FP16 and INT8 where applicable.

• Evaluate model performance across different hardware platforms and inference frameworks, covering latency, throughput, memory usage, accuracy, and resource utilization.

• Analyze performance bottlenecks, troubleshoot model compatibility and runtime issues, and propose practical optimization solutions. • Build reusable scripts, test cases, benchmarks, and technical documentation for model deployment and performance evaluation.

• Collaborate with algorithms, platform, and integration engineers to support model delivery and customer demonstration activities. • What Makes You A Strong Fit • Currently pursuing a Bachelor’s or master’s degree in computer science, Artificial Intelligence, Electronic Engineering, Automation, Automotive Engineering, or a related field.

• Available at least 3 days per week for a minimum internship period of 3 months. • Solid programming skills in Python and C/C++, with a good understanding of data structures, algorithms, and Linux development environments.

• Familiar with deep learning model formats and deployment workflows, especially ONNX. • Hands-on knowledge of one or more inference and optimization frameworks, such as Open VINO, TensorRT, TVM, or Qualcomm QNN.

• Understanding model optimization techniques such as graph optimization, operator fusion, precision conversion, calibration, pruning, and quantization.

• Ability to design reproducible performance tests, analyze results, and clearly document technical findings. • Good analytical, problem-solving, communication, and teamwork skills; able to learn independently and work across teams.

Bonus Points if You Have • Project, research, competition, or internship experience in model deployment, edge AI, embedded AI, or heterogeneous computing.

• Experience with NVIDIA Jetson, Qualcomm Snapdragon platforms, Samsung Exynos, or other embedded accelerators. • Experience using profiling tools such as NVIDIA Nsight Systems, TensorRT profiling utilities, OpenVINO benchmark tools, or platform-specific profilers.

• Knowledge of computer vision models, transformer models, or automotive AI applications such as DMS, OMS, gesture recognition, and intelligent cockpit features.

• Experience with Git, CMake, Docker, CI/CD, cross-compilation, or automated benchmarking. • Strong interest in emerging AI acceleration technologies and the ability to quickly learn new hardware and software toolchains.

Things To Know • Willingness to work in an office. • You have a working knowledge of English. What You Can Expect • Learning and development opportunities through our award-winning HARMAN University programs.

• Wellness benefits designed to support your overall well-being. • Access to the HARMAN campus fitness center and cafeteria, where available. • An inclusive and diverse work environment that supports both your professional and personal development.

HARMAN is proud to be an Equal Opportunity / Affirmative Action employer . All qualified applicants will receive consideration for employment without regard to   race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics.

Verified by UTern

Last read under an hour ago · pay stated in the listing

More at HARMAN

Other roles this employer has live right now.