Responsibilities
Design and build statistical and algorithmic detection tools for wafer probe data — including test hardware integrity checks, software bin/yield outlier detection, parametric drift analysis, and reticle- and wafer-level spatial pattern classification — leveraging Semtech's existing statistical infrastructure (20%)
Assist on the development of learned pattern-recognition models that classify wafer-level failure patterns from engineer-confirmed examples, complementing the statistical tool set and supporting multi-pattern classification with confidence indicators. Risk-tiering, prioritization, and mitigation-proposal logic — including known-issue catalog matching, lot-level systemic risk reporting, and drafting of wafer-map modification scripts (20%)
Drive along with the tool software teams the buildup of relationship-analysis and reporting layer that reconciles detection outputs into a consolidated set of distinct issues, including LLM-driven contextualization using product and test/bin naming data, and structured, self-describing output for downstream risk assessment (20%)
Identify and drive development and requirements for AI process improvement initiatives among the quality engineering teams. (20%)
Partner with Quality Engineering, Product Engineering, and the AI development team to validate system performance against production fab lots, and produce documentation and knowledge-transfer materials that support long-term, in-house ownership of the system (20%)
Minimum Qualifications
Bachelor's degree in Electrical Engineering, Computer Science, Statistics, or a related field required; Master's or PhD preferred
5+ years of professional experience in software engineering, applied statistics, or data science, with a track record of shipping production statistical or machine-learning systems
Strong foundation in applied statistics, including outlier and anomaly detection, multiple-comparison correction, and hypothesis testing on production or sensor data
Hands-on experience building and deploying machine learning classification models, including training on labeled data and handling out-of-distribution/novel-category detection
Proficiency in Python (or equivalent) for data analysis and ML model development, and strong SQL or equivalent skills for working with large structured production datasets
Demonstrated ability to design structured, self-describing system outputs and to write clear technical documentation for engineering audiences
Desired Qualifications
Experience with semiconductor test data, wafer probe, or final test engineering, including familiarity with concepts such as software binning, parametric test limits, and wafer map analysis
Direct experience with a comparable semiconductor test-data / yield-analysis platform
Experience building LLM-driven analysis or reporting systems that incorporate domain context to scope and focus model output
Familiarity with spatial/statistical process control methods (e.g., Tukey-method outlier detection, radial/angular trend analysis, spatial clustering) as applied to manufacturing data
Prior experience working in a regulated or quality-critical manufacturing environment where system outputs feed formal disposition or non-conforming material review processes
The intent of this job description is to describe the major duties and responsibilities performed by incumbents of this job. Incumbents may be required to perform job-related tasks other than those specifically included in this description.
All duties and responsibilities are essential job functions and requirements and are subject to possible modification to reasonably accommodate individuals with disabilities.
We may leverage Artificial Intelligence (AI) tools to enhance efficiency during candidate screening, assessment, and recruitment. Final hiring decisions remain with our Hiring Teams, not AI systems.
A reasonable estimate of the pay range for this position is $95,000CAD-$120,000CAD There are several factors taken into consideration in determining base salary, including but not limited to: job-related qualifications, skills, education and experience, as well as job location and the value of other elements of an employee’s total compensation package.
