Job Title
Staff / Principal Physical Design Engineer
Staff / Principle Physical Design Engineer
About Cognichip
At Cognichip, we are building AI-native tools that transform how semiconductor engineers create, verify, and optimize chips. Our platform combines large proprietary models, agentic workflows, domain-specific engineering intelligence, and high-performance simulation infrastructure to accelerate one of the world’s most complex engineering disciplines.
About The Role
We are seeking a Staff / Principal Physical Design Engineer to lead the development of next-generation AI workflows for ASIC implementation. In this role, you will bridge deep physical design expertise with advanced AI capabilities to enhance ASIC design and signoff. You will serve as a technical anchor blending hands-on physical design experience, EDA methodology leadership, and AI-driven automation. This work is critical to Cognichip's mission of expanding design automation, reducing cycle times, and optimizing PPA.
Key Responsibilities
As a key technical leader driving AI-native physical design methodology, you will:
- Architect and build production-grade AI agents and automated workflows for physical design tasks across implementation and signoff.
- Define central CAD flows, Central Flow & Methodology (CFM) primitives, and scriptable infrastructure for advanced technology nodes (e.g., 7nm, 5nm, 3nm).
- Combine domain-specific chip design knowledge with modern AI/ML models to predict PPA early and optimize timing/power closure.
- Collaborate closely with AI research engineers, software developers, and physical design teams to translate complex implementation bottlenecks into AI-assisted solutions.
- Drive technical evaluation, tooling recipes, and methodologies for customer-facing deployment and internal EDA automation platforms.
- Establish rigorous quality gates, static checks, verification infrastructure, and architectural guardrails for AI-generated physical design scripts and constraints.
Required Qualifications
- Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, Computer Science, or a closely related technical field.
- 10–15+ years of hands-on physical ASIC design and methodology experience, spanning full RTL-to-GDSII implementation, static timing analysis (STA), clock tree synthesis, floorplanning, power integrity, and physical verification.
- Mastery of industry-standard EDA physical design and STA tool suites (e.g., Synopsys Fusion Compiler, PrimeTime, IC Compiler II; Cadence Innovus, Genus, Tempus).
- Proven track record in EDA CAD automation, script infrastructure development (Tcl, Python, Perl, Shell), flow governance, and methodology standardization across multi-site engineering teams.
- Demonstrated experience or strong applied interest in leveraging AI/ML techniques (e.g., agentic LLM workflows, early PPA prediction, or ML-guided optimization) to enhance hardware design flows.
Preferred Qualifications
The following items are not required but are great bonuses:
- Experience with advanced technology nodes (7nm, 5nm, 3nm) and complex multi-corner multi-mode (MCMM) timing signoff, UPF low-power design, and EM/IR mitigation.
- Familiarity with recent and emerging research in machine-learning-based methods for hardware design, modeling and implementation.
- Hands-on experience developing or integrating AI coding agents, tool-use frameworks, or automated design and debugging flows.
Prior experience working at the intersection of EDA startups, AI research, and silicon design execution.
What It's Like Here
- We’re a fast-moving AI startup with a collaborative, high-trust culture.i
- We value technical excellence, ownership, and the freedom to experiment.
- Our best work happens when our builders and innovators work closely together to turn ambitious ideas into category defining products.
- We operate on a hybrid schedule with four days in office, one day remote.
- If you’re excited to build cutting edge tools that empower semiconductor engineers and reshape how chips are designed, you’ll feel right at home.
Note
Level will be determined after the panel interview commensurate with transferable experience.