Female-founded semiconductor AI startup SixSense raises $8.5M

A Deep Tech Startup -based in Singapore called Sixsen has developed an AI-driven platform that helps manufacturers of semiconductors to predict and detect potential chip defects on production lines in real time.

It has collected $ 8.5 million in Series A that yields its total financing to around $ 12 million. De Ronde was led by Peak XV’s Surge (formerly Sequoia India & Sea), with the participation of Alpha Intelligence Capital, Febe and others.

SixSense was founded in 2018 by engineers Akanksha Jagwani (CTO) and AVNI AGARWAL (CEO) and wants to take on a fundamental challenge in the production of semiconductors: converting raw production data, from defections to improving and the race to improve quality problems.

Despite the enormous number of data generated on the FAB floor, what stood out the co-founders was a surprising lack of real-time intelligence.

Akanksha gives a deep understanding of production, quality control and software automation through its experience in building automation solutions for manufacturers such as Hyundai Motors and GE and LED product development at startups such as Embibe. Agarwal adds technical experience from her time at Visa, where she built large-scale data analysis systems, some of which were later protected as trade secrets. A competent coder with a strong background in mathematics, she had long been interested in applying AI to traditional industries outside of Fintech.

Together the duo evaluated aviation sectors to the car before he landed on semiconductors. Despite the reputation of the semiconductor industry for precision, inspection processes remain largely manually and fragmented, AGARWAL told WAN. After she had spoken with more than 50 engineers, it became clear that there is an important space to modernize how quality controls are being carried out, she added.

Nowadays, Fabs are filled with dashboards, SPC maps and inline inspection systems, but most only give data without further analysis, said Agarwal. “The burden to use it for decision -making still falls on engineers: [they must] Spot patterns, examining anomalies and trace causes. That is time -consuming, subjective and does not scale well with increasing process complexity. “

SixSense offers engineers early warnings to tackle potential problems before escalating with possibilities such as defective detection, root cause analysis and failure forecast.

The SixSense platform is also specifically designed to be used by processing engineers instead of data scientists, said Agarwal. “Processing engineers can refine models using their own FAB data, implement them in less than two days and trust the results all the way without writing a single line of code. That makes the platform both powerful and practical.”

The competitive landscape includes internal technical teams that use aids such as Cognex and Halcon, makers of inspection equipment that integrate AI into their systems and startups, including Landing.ai and Robovision.

The SixSense AI platform is already in use at large manufacturers of semiconductors such as Globalfounders and JCET, with more than 100 million chips processing so far. Customers have reported up to 30% faster production cycles, a boost of 1-2% in yield and a reduction of 90% in manual inspection work, according to the founders. The system is compatible with inspection equipment that covers more than 60% of the worldwide market.

“Our target customers are large-scale chip makers, including foundries, outsourced semiconductor composition and test providers (OSATs) and integrated manufacturers of devices (IDMS),” said Agarwal. “We are already working with Fabs in Singapore, Malaysia, Taiwan and Israel, and are now expanding to the US”

Geopolitical tensions, especially between the US and China, reform where chips are made, so that new production investments are controlled all over the world.

“We see Fabs and Osats aggressively expanding in Malaysia, Singapore, Vietnam, India and the US and That is a tail wind for us. Because we are already established in the region, and many of these new facilities start fresh-without legacy systems that she weighs.