AI/ML Engineer

Join Test Development team and help build AI and machine-learning solutions that accelerate silicon test, validation, debug, and engineering productivity.
In this role, you will work across two closely connected areas: developing machine-learning solutions for large volumes of manufacturing, test, and validation data, and building agentic AI systems that help engineers reliably access, reason over, and interact with complex hardware and engineering information.
You will develop AI agents, retrieval-augmented generation (RAG) pipelines, evaluation frameworks, machine-learning models, and analytics tools that integrate with engineering documentation, source code, databases, test infrastructure, and EDA systems. These solutions will be used by multiple engineering teams to improve test efficiency, accelerate debug, identify patterns and anomalies, and make engineering knowledge easier to access.
This is a hands-on role well suited to an early-career engineer with strong Python skills, solid machine-learning fundamentals, and practical experience building applications with LLMs or AI agents. The ideal candidate is curious, analytical, comfortable working with complex technical data, and interested in applying modern AI techniques to real-world semiconductor engineering problems.

Job Responsibilities:
- Build and maintain agentic AI systems, including agents, tool integrations, orchestration, and multi-step workflows.
- Develop RAG pipelines for technical documentation and source code, including parsing, chunking, embeddings, vector search, retrieval, and reranking.
- Implement tool/function calling, structured outputs, context management, and prompt-grounding techniques.
- Develop evaluation frameworks to measure retrieval quality, answer accuracy, tool-use correctness, reliability, and latency.
- Integrate AI solutions with engineering tools, APIs, databases, source repositories, test infrastructure, and EDA systems.
- Prepare and analyze large silicon tests, manufacturing, validation, and debug datasets.
- Develop ML models for classification, clustering, anomaly detection, pattern analysis, and failure analysis.
- Build reusable Python analytics and automation tools to support debug and root-cause analysis.
- Write maintainable code, document experiments and result, and collaborate with cross-functional engineering teams.

Qualifications:
- Bachelor s or Master s degree in Computer Science, Data Science, AI/ML, Electrical Engineering, or equivalent.
- 1-2 years of hands-on experience in Machine Learning, Generative AI, or Agentic AI through work, internships, research, or projects.
- Strong proficiency in Python, with experience in NumPy, pandas, and scikit-learn.
- Solid understanding of ML fundamentals, including supervised/unsupervised learning, feature engineering, anomaly detection, model evaluation, overfitting, and regularization.
- Understanding of LLM and Generative AI fundamentals, including embeddings, transformers, context windows, prompting, and structured outputs.
- Familiarity with Agentic AI, including tool/function calling, task decomposition, orchestration, and multi-step workflows.
- Familiarity with RAG, vector databases, semantic search, chunking, embeddings, and retrieval evaluation.
- Hands-on experience with an LLM API, agent framework, or RAG framework is preferred.
- Basic experience with REST APIs, JSON, Linux, and Git-based workflows.
- Exposure to AI evaluation/observability, MCP, Claude Code/Agent SDK, or semiconductor test/EDA environments is a plus.
- Strong analytical, problem-solving, documentation, and communication skills.

Top Mandatory Skills: Python, ML/GenAI/Agentic AI fundamentals, LLM, RAG

Nice to have Secondary Skills: MCP, Claude Code / Agent SDK

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.