Product Lead, Yield Engineering

Vision

Root cause analysis in semiconductor manufacturing is still largely manual — a senior yield engineer pulls data from MES, defect inspection, metrology, parametric test, and equipment logs to work out what changed. It is slow, hard to scale, and dependent on the experience of engineers that rarely captured for the next investigation.

AI-RCA uses agents to continuously ingest data across the fab and packaging line, correlates signals that would take a human hours or days to connect, proposes likely root causes the engineer can verify, and learns from every case. It is not a replacement for the yield engineer but an assistant for them that never sleeps, never forgets a past excursion and does the mundane work for the yield engineer to verify.
Impact and value

• Faster RCA and containment of excursions, reducing yield exposure.

• A more accurate tool holds, improving process tool productivity.

• Higher engineering productivity through faster, better-supported investigations.

• Retained tribal knowledge held by a small number of senior engineers.

The role

AI agents are about to change how fabs run. This role sits at the centre of that change. As the bridge between customer fab engineering teams and our data science and software teams, you will help shape a new generation of agents that reason about yield, defects, and process behaviour the way a senior engineer does — only faster, across more data, and with memory that compounds across every investigation. The agents we are building today will define how the next decade of semiconductor manufacturing works, and this role gets to influence both the product and the intelligence behind it.

What you'll do

Customer engagement and data integration

• Data Alignment: Work with customer yield, integration, and IT teams to align on the datasets the system needs to integrate with — MES, Klarity, defect inspection, metrology, equipment logs, and others, depending on the fab.

• Data validation: Validate customer data on completeness, correctness, and consistency. Identify gaps, anomalies, or quality issues that would affect output reliability.

• Customer context: User understands each customer's specific needs, priorities, and constraints — which use cases matter most, which data sources are accessible or sensitive, and what level of automation they are comfortable with.

Product design and feedback to engineering

• Data science feedback: Provide structured feedback to the data science team on agent behaviour: where the system performs well, where it falls short, what factors should be weighted differently, and how exceptions should be handled.

• Software feedback: Provide structured feedback to the software team on user workflows from a yield engineer's perspective: how the platform is used during an excursion, how the engineer interacts with findings, and what scenarios the product must handle gracefully.

• I/O and automation: Align with both teams on inputs, outputs, and the appropriate level of automation at each stage.

• Foundational gaps: Identify areas that need to be strengthened — knowledge base content, defect classification accuracy, taxonomy coverage, and similar.

System-level alignment

• Success criteria: Participate in discussions on speed, accuracy, throughput, and other success criteria. Translate customer expectations into specifications that the engineering team can build against.

• Performance tracking: Track how the product is performing against these criteria across deployments and bring issues into the roadmap.

Bridging customers and the SixSense team

• Technical bridge: Serve as the primary technical bridge between customer engineering teams and our internal data science and software teams. Translate customer context into product requirements, and product capabilities into language that customers can act on.

• Customer trust: Build the kind of relationship with customer yield teams where their feedback comes to us early and honestly, rather than surfacing as escalations after the fact.

What we're looking for

• 4+ years in yield or process engineering at an IDM, foundry, OSAT, or fab.

• Experience across both wafer fab and packaging environments, or deep experience in one with working familiarity with the other.

• Hands-on experience leading root cause analysis on production yield excursions.

• Working familiarity with the inspection and metrology data types that drive RCA — Wafer defect inspection, SPC, Metrology, FDC, lot history, reports, etc

• Familiarity with fab data systems such as MES, Klarity, or equivalent yield management and analytics platforms.

• Strong understanding of correlations between defects, wafer map signatures, scan steps, process tools, technology and other factors that help with RCA

• Conceptual familiarity with machine learning and the ability to engage substantively with data science engineers on model behaviour and outputs.

• Comfort in a customer-facing role — clear communicator, able to hold technical conversations at depth without losing non-technical stakeholders.