P

Positron

Memory-first AI inference silicon for LLMs

Senior ASIC Physical Design Engineer - DFT

Hardware Validation & TestingPosted on Nov 11
Full-timeAustin, TX, USAIn-person

About the Job

Requirements

  • A BS, MS, or PhD in Electrical Engineering or Computer Engineering is required.
  • At least 8 years of ASIC development experience is required.
  • Extensive hands-on DFT implementation experience on complex SoCs, including multiple successful production tapeouts, is required.
  • Deep understanding of scan architectures and their implementation is required, including ATPG, memory BIST and repair, boundary scan, IJTAG, EDT, fault models, and structural coverage analysis.
  • Hands-on experience with Siemens Tessent DFT solutions, including SSN, EDT, MBIST, RTLpro, Scanpro, and Tessent Diagnosis, is required.
  • Strong RTL design skills using Verilog or SystemVerilog are required.
  • Practical experience with synthesis and gate-level verification is required.
  • Strong scripting ability in Python, Tcl, Perl, or similar languages is required.
  • Strong debugging skills across RTL, netlists, and silicon failure analysis are required.
  • Ability to drive technical execution across cross-functional engineering teams is required.

Responsibilities

  • Own DFT implementation end-to-end, from defining DFT micro-architecture for accelerators through integration into internal RTL and third-party IP, implementation with the backend design partner, and pre-silicon validation for silicon bring-up.
  • Micro-architect and implement DFT instrumentation logic, including scan insertion, compression, ATPG, memory BIST, boundary scan (IEEE 1149.x), IJTAG (IEEE 1687) infrastructure, and debug and observability features.
  • Integrate DFT IP into internally developed RTL and evaluate and integrate DFT capabilities from third-party IP providers.
  • Work directly in RTL, synthesis, and DFT tool flows.
  • Develop comprehensive DFT verification plans and validate DFT functionality through simulation and gate-level verification.
  • Drive stuck-at, transition, cell-aware, and power-aware ATPG strategies and ensure DFx coverage targets are achieved before tapeout.
  • Work closely with backend implementation teams to ensure successful physical realization of the DFT architecture.
  • Guide scan chain partitioning, compression planning, and test clock architecture.
  • Address power-aware test implementation, timing closure considerations, and test mode integration.
  • Partner with RTL design, design verification, physical design, package and test engineering, firmware, system software, and silicon validation teams to ensure DFT solutions remain correct, compliant, complete, and consistent through silicon bring-up.
  • Use AI tools to improve engineering productivity through automated review of DFT reports, ATPG and coverage analysis, regression triage, documentation generation, workflow automation, and agentic engineering assistants.

Desired Qualifications

  • Experience with high-performance AI accelerators, GPUs, CPUs, networking ASICs, PCIe, HBM, LPDDR, or chiplet architectures.
  • Exposure to high-speed SerDes and advanced process nodes of 5nm and below.
  • Background in low-power design, yield enhancement methodologies, and manufacturing test optimization.
  • Hands-on experience with silicon bring-up, failure analysis, and post-silicon debug.
  • Understanding of secure manufacturing and DFT, including interactions among secure boot, hardware root of trust, scan access control, fuse programming, key management, and production test.
  • Experience architecting in-system debug and observability infrastructure, including trace, event logging, test registers, and scan visibility, to accelerate emulation and first-silicon bring-up.
  • Familiarity with emulation and pre-silicon validation platforms such as Palladium, ZeBu, Veloce, or FPGA prototyping to validate DFT features before tapeout.

About the Company

Positron

Memory-first AI inference silicon for LLMs

Positron develops memory-first AI inference silicon and systems to scale large-language-model serving. Its Atlas systems rely on commodity LPDDR5X memory rather than expensive HBM/CoWoS to boost bandwidth and capacity, enabling more efficient LLM deployment at hyperscale. The company’s next-generation Asimov silicon (tape-out planned for late 2026; production in 2027) pairs compute with very large memory per chip (roughly 288 GB to 2,304 GB) and is designed to be combined into Titan configurations (four to eight Asimov chips) for extremely large models and long context windows. Positron has already deployed Atlas systems in the cloud, including 50+ racks at Oracle Cloud Infrastructure and partnerships with Parasail, Jump Trading, and i3d.net. Its goal is to provide scalable, memory-rich AI inference hardware that lowers cost and increases throughput for serving large language models.

Company size
51-200
Company stage
Series C
Total funding
$1.2B
Headquarters
Reno, NV
Founded
2023

Recently Posted Jobs

Explore more opportunities at Positron

See more jobs