👋 About the Team
The NetsPresso Platform Team is responsible for designing and building the core platforms and software that bring Nota AI’s model compression and optimization technologies from research into real-world products.
The team is composed of Model Representation, Quantization, Graph Optimization, Model Engineering, and Software Engineering functions. NetsPresso converts models from various deep learning frameworks into its proprietary unified intermediate representation (NPIR), and applies optimization techniques such as quantization, graph optimization, and compression to maximize inference efficiency across diverse target hardware environments (NPU, GPU, CPU).
📌 What You’ll Do at This Position
In this role, you will work directly with real customer models and target hardware environments, leveraging NetsPresso’s optimization technologies to deliver “optimization that works in production.” Rather than simply providing tools, you will analyze model architectures alongside constraints such as accuracy, latency, and memory, and implement the most effective optimization strategies tailored to each use case.
✅ Key Responsibilities
- Customer Model Optimization Projects
- Analyze customer Gen AI model architectures and establish optimization strategies
- Perform model conversion, optimization, and validation using the NetsPresso technology stack
- Conduct trade-off analysis across accuracy, latency, and memory, and optimize models based on customer requirements
- Target Hardware Optimization
- Optimize Gen AI models for on-device NPU environments, considering hardware-specific characteristics
- Deploy models using NPU backend compilers and validate performance
- Analyze and resolve model conversion and deployment issues arising from hardware constraints
- Contribution to NetsPresso Productization
- Translate customer requirements and technical issues from the field into product improvements
- Systematize recurring optimization workflows into automation tools, scripts, and internal libraries
✅ Requirements
- Bachelor’s degree or higher in Computer Science, Electrical Engineering, or a related field
- 3+ years of relevant industry experience
- Hands-on experience in model development, conversion, and inference using deep learning frameworks such as PyTorch, ONNX, or TFLite
- Experience applying optimization techniques such as quantization, graph optimization, or compression to real-world models
- Familiarity with Linux, Git/GitHub, and Docker
- Comfortable communicating and collaborating with customers or external partners on technical topics
- No restrictions on domestic or international business travel
✅ Pluses
- Experience applying optimization techniques (e.g., quantization, graph optimization, compression) to generative AI models such as LLMs or VLMs
- Experience deploying and optimizing models for on-device NPU environments
- Hands-on experience with optimization/compilation libraries such as ExecuTorch, TensorRT, TFLite, OpenVINO, or AIMET
- Understanding of compilers and intermediate representations (e.g., MLIR, ONNX, TVM) and graph optimization passes
- Experience in roles such as Field Application Engineer, Solutions Engineer, or technical consultant at hardware vendors or AI solution companies
✅ Hiring Process
- Document Screening → 1st Interview → 2nd Interview → 3rd Interview → Offer → Hire
(Additional assignments may be included during the process.)
🤓 A Message from the Team
This role offers a unique opportunity to work at the forefront of bringing NetsPresso’s technology out of the lab and into real-world customer products. You will directly face the challenges of deploying Gen AI models onto on-device NPUs, transforming “theoretically possible optimizations” into “optimizations that actually work in production.” We are looking for someone who enjoys this process—someone who can understand both the language of customers and engineers, and proactively translate field feedback into product improvements. If you are eager to push the boundaries of on-device AI in real-world environments, this role will offer you both rapid growth and the opportunity to create meaningful impact.
Please Check Before Applying! 👀
- This job posting is open continuously, and it may close early upon completion of the hiring process.
- Resumes that include sensitive personal information, such as salary details, may be excluded from the review process.
- Providing false information in the submitted materials may result in the cancellation of the application.
- Please be aware that references will be checked before finalizing the hiring decision.
- Compensation will be discussed separately upon successful completion of the final interview.
- There will be a probationary period after joining, and there will be no discrimination in the treatment during this period.
- To support the employment of persons with disabilities, you may optionally submit a copy of your disability registration certificate under “Additional Documents,” if administrative verification is required. Submission is optional and does not affect the evaluation process.
- Veterans and individuals with disabilities will receive preferential treatment in accordance with relevant regulations.
🔎 Helpful materials
