About Unconventional
Since 2022, AI has entered the mainstream, reshaping entire industries from education and software development to fundamental consumer behaviors. This revolution has created an unprecedented demand for computation—a demand that is now fundamentally limited by energy, not just in the datacenter, but at a global scale.
At Unconventional, our mission is to solve this. We are rethinking computing from the ground up to build a new foundation for AI that is 1000x more efficient. We're doing this by exploiting the rich physics of semiconductors, mapping neural networks directly to the device physics rather than relying on layers of inefficient abstraction.
The Role
As a Member of Technical Staff, DFT Engineer, you will be a foundational member of our multi-disciplinary R&D team. We are looking for individuals who thrive at the intersection of architecture and silicon, turning novel AI concepts into high-performance, energy-efficient hardware. You will be responsible for the testability realization of our novel computing platform, ensuring that our complex digital logic and custom mixed-signal blocks can be reliably tested.
Responsibilities
DFT Architecture & Implementation: Lead the implementation of comprehensive test architectures using industry-standard CAD tools. This includes the insertion, configuration, and verification of scan compression, Memory Built-In Self-Test (MBIST), and JTAG/boundary scan logic.
Hierarchical DFT Implementation: Drive bottom-up hierarchical DFT methodologies for large-scale SoC designs, managing core-level test wrapping, pattern retargeting, and top-level test integration to optimize runtime and capacity limits.
Foundry Interface & Defect Analysis: Own the overarching DFT strategy, working closely with foundry interfaces to analyze defect densities and drive yield improvements for test chips.
Multi-Stacked Die DFT: Drive cutting-edge DFT methodologies for 2.5D/3D multi-stacked die packaging. You will ensure comprehensive test coverage across die-to-die interfaces utilizing emerging standards like IEEE 1838.
Analog Macro DFT: Work at the interface of digital and analog design to facilitate the integration and testability of custom analog mixed-signal blocks. You will develop novel test strategies for non-standard analog macros operating within the digital fabric.
Test & PPA Optimization: Drive aggressive test coverage, test time, and yield targets while working closely with architects to influence the micro-architecture for better Power, Performance, and Area (PPA).
Sign-off & Verification: Own the final DFT sign-off process. This includes Automatic Test Pattern Generation (ATPG), test vector validation, fault simulation, and ensuring clean timing closure during Static Timing Analysis (STA) for all test modes.
Methodology Development: Contribute to the development and automation of our design flow. Set best practices for testability to ensure first-pass silicon success.
Partner Engagement: Work to evaluate potential partners that offer AI tools that could greatly improve chip design efficiency.
Minimum Qualifications
Education: B.S. or M.S. in Electrical Engineering, Computer Engineering, or a related field.
Experience: 10+ years of industry experience in digital DFT and test architecture, with a track record of successful tapeouts on modern process nodes (7nm, 5nm, or newer preferred).
Technical Expertise:
Deep expertise in scan compression, MBIST generation, fault modeling (stuck-at, transition, path delay), and ATPG.
Deep understanding of physical design challenges in advanced nodes (multi-patterning, finFET effects, low-voltage operation) and their impact on test reliability.
Expertise in Static Timing Analysis (STA) and timing closure for complex designs in shift and capture test modes.
Design Flow Proficiency:
Expert-level mastery of standard EDA CAD tool suites for DFT implementation and vector generation.
Strong scripting skills in Tcl, Python, or Perl to automate design flows and data analysis.
Communication: Excellent written and verbal communication skills, with experience managing deliverables from external vendors or design houses.
Preferred Qualifications (Nice to Have)
Advanced Packaging Test: Hands-on experience with modern die-to-die (D2D) interconnect test strategies, chiplet testing, and 3D-IC DFT architectures.
Custom AI Hardware: Experience with test architecture for Machine Learning accelerators or large-scale systolic arrays.
Mixed-Signal Integration: Experience with top-level integration of large, custom analog macros and complex power-sequencing requirements.
AI Tools: Familiarity with state of the art AI tools to accelerate chip design.
Why Join Us?
The Mission: Redefine computing for the next 50 years by solving the fundamental energy limitation of AI at a global scale.
The Impact: Shape the company's future as a foundational team member. Enjoy massive ownership and an outsized opportunity to drive change.
The Challenge: Dive into deeply complex, intellectually stimulating, and unsolved problems at the cutting edge of multiple, converging fields.
The Perks: A comprehensive package including best-in-class health benefits, 401k matching, truly unlimited PTO, and complimentary meals in our Mountain View office.
Unconventional AI is rethinking the foundations of computing to optimize energy efficiency for AI workloads. Founded by pioneers including Naveen Rao (Nervana, MosaicML) and Michael Carbin (MIT, MosaicML), the company is building a new computational substrate that interfaces directly with the physics of silicon to achieve biology-scale efficiency. They have recently raised $475M in seed funding to develop this physics-based computing system designed specifically for machine learning applications. The company's approach involves developing multi-disciplinary simulation frameworks that enable rapid iteration and testing across all layers of their unconventional computing systems.
