Role Overview:
As an R&D Engineer, you will work on cutting-edge AI and machine learning solutions, with a focus on Large Language Models (LLMs), to enhance semiconductor testing and electrotechnical systems. You will design, implement, and optimize end-to-end AI pipelines, integrating LLM-driven tools into testing workflows and contributing to the development of advanced semiconductor test automation.
Key Responsibilities:
- Design, implement, test, and continuously optimize end-to-end RAG (retrieval-augmented generation) pipelines, including data parsing, ingestion, prompt engineering, and chunking strategies.
- Curate and develop high-quality datasets, including synthetic data generation for robust training and evaluation of LLMs.
- Preprocess datasets, fine-tune open-source LLMs (e.g., LLaMA, Mistral), and integrate RAG systems into semiconductor testing pipelines.
- Rigorously evaluate LLM applications on correctness, latency, and hallucination metrics.
- Assist in deploying LLM-based applications, analyze user feedback, and contribute to iterative improvements.
- Write clean, maintainable, and testable code following software engineering best practices.
- Collaborate with cross-functional agile teams to translate customer requirements into prototype solutions, with opportunities to lead smaller sub-projects.
- Analyze semiconductor testing data (parametric measurements, yield logs) using statistical methods and visualization tools.
- Contribute to MLOps workflows for model training, evaluation, and deployment using Python frameworks (PyTorch, Hugging Face) and cloud platforms (AWS/Azure).
- Integrate AI components with existing systems, requiring experience in Java or C++ and familiarity with Eclipse.
- Work in Linux environments and handle command-line tools, scripting, and system operations.
Preferred Qualifications
- University degree in Data Science, Computer Science, Electrical Engineering, or a related field (Master’s preferred, Bachelor’s with 2+ years’ experience accepted).
- 1–3 years of hands-on experience in machine learning, including coursework or practical work with NLP or LLMs.
- Proficiency in Python for data analysis (Pandas, NumPy) and ML model development (scikit-learn, PyTorch).
- Experience programming in Java or C++.
- Strong understanding of Linux, including command-line usage, system navigation, and scripting.
- Familiarity with LLM concepts: transformer architectures, prompt engineering, text generation techniques.
- Foundational knowledge of MLOps practices: version control (Git/DVC), containerization (Docker), and cloud deployment.
- Experience with Jupyter notebooks or VS Code.
- Strong communication skills in English; ability to document technical work clearly.
- Exposure to semiconductor testing data or industrial IoT datasets.
- Experience with RAG systems, LLM fine-tuning workflows (LoRA, QLoRA).
- Familiarity with integrating AI components into existing test platform codebases.
- Elementary German proficiency.
This is a plus:
- Experience with Advantest V93000 test systems
- Experience in Eclipse Plugin development
Top Skills
What We Do
For over a half-century, Advantest has been designing innovative electronic measuring equipment and semiconductor test systems essential to the development and manufacture of advanced computer and telecommunications products. On April 1, 2012, Advantest completed its integration of Verigy Ltd.
Additional Information about Advantest can be found at www.advantest.com.
