SixSense, a semiconductor AI startup founded by a woman, raises $8.5 million

A deep tech startup based in Singapore is being called Sixth Sense We have developed an AI-powered platform that helps semiconductor manufacturers predict and detect potential chip defects in their production lines in real time.

It raised $8.5 million in Series A, bringing its total funding to around $12 million. The round was led by Peak XV’s Surge (formerly Sequoia India & Sea) with participation from Alpha Intelligence Capital, Febe and others.

Founded in 2018 by engineers Akanksha Jagwani (CTO) and Avni Agarwal (CEO), SixSense aims to address the fundamental challenges in semiconductor manufacturing. The aim is to convert production data from defective images to equipment signals.

Despite the enormous amount of data generated on the fab floor, what stood out for the co-founders was the surprising lack of real-time intelligence.

Akanksha is a startup such as Embibe and experiences automation solutions such as manufacturers such as Hyundai Motor and GE, as well as LED product development, and provides a deeper understanding of manufacturing, quality control and software automation. Agarwal added his technical experience with Visa where he built a large-scale data analysis system. Some of them were later protected as trade secrets. A skilled coder with a strong background in mathematics, she has long been interested in applying AI to traditional industries other than fintech.

Together, the duo assessed the sector from aviation to automobiles before landing in the semiconductor. Despite the reputation of the semiconductor industry for accuracy, the testing process remains largely fragmented manually, Agarwal told TechCrunch. After talking to more than 50 engineers, it was revealed that there is a critical space that modernizes how quality checks are done, she added.

Today’s FABS is filled with dashboards, SPC charts and inline inspection systems, but in most cases it only displays data without further analysis, Agarwal said. “The burden of using it for decision-making still applies to engineers. (They) investigate spot patterns, anomalies and trace the root cause. It is time-consuming, subjective, and does not expand sufficiently to match the increasing complexity of the process.”

SixSense provides early warnings for engineers to address potential issues before escalating into features such as defect detection, root cause analysis, and failure prediction.

SixSense’s platform is specifically designed for use by process engineers rather than data scientists, Agarwal said. “Process engineers can use their own fab data to fine-tune the model, deploy it within two days, and trust the results. All without writing code, making the platform powerful and practical.”

Competitive situations include tools like Cognex and Halcon, testing equipment manufacturers that integrate AI into systems, and in-house engineering teams using startups like Landing.ai and Robovision.

SixSense’s AI platform is already used by major semiconductor manufacturers such as GlobalFoundries and JCET, and has processed more than 100 million chips to date. Customers report production cycles up to 30% faster, with yields increased by 1-2% and manual inspection work reduced by 90%, the founders said. This system is compatible with testing equipment covering more than 60% of the global market.

“Our target customers are large ship manufacturers, including foundries, outsourced semiconductor assemblies and test providers (OSATS), and integrated device manufacturers (IDMS),” Agarwal said. “We have already worked with Fabs from Singapore, Malaysia, Taiwan and Israel, and are now expanding to the US.”

Geopolitical tensions, particularly between the US and China, are restructuring where chips were created and driving new manufacturing investments around the world.

“We see the aggressive expansion of Fab and Osat in Malaysia, Singapore, Vietnam, India and the US. That’s a tailwind for us, because we are already based in the region and many of these new facilities are fresh.