Software Engineer, GenAI Silicon Automation, DeepMind

Bridge the velocity gap between rapidly evolving ML models and hardware design cycles by automating the entire silicon lifecycle. We aim to transform hardware design into a continuous, agent-driven process. We are working at the intersection of machine learning for systems and hardware design for machine learning accelerators. We conduct applied research and development in multiple areas of machine learning, operation research, compiler construction, hardware design and synthesis, in collaboration with product teams across Alphabet.

We are looking for software engineers who are passionate about building infrastructure for hardware design tools. In this role, you will be part of a research team conducting exploratory research and engineering towards designing systems using AI. You will have an opportunity for a strong impact. Knowledge or prior experience in hardware design and/or AI is a plus, but it is not a requirement.

Artificial intelligence will be one of humanity’s most transformative inventions. At DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.

Individual pay is determined by factors including job-related skills, experience, and relevant education or training.

US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google.

Responsibilities

• Architect, scale, and maintain our custom multi-agent orchestration systems and execution coordinators.
• Design and maintain high-fidelity evaluation suites (evalsets) specifically representing complex hardware design tasks, spanning both high-level design specification inputs and physical synthesis tool runs.
• Engineer modular carve-outs of our flow to run seamlessly as standalone tools within downstream customer environments.
• Build and optimize hardware compilation pipelines in MLIR/CIRCT, translating agentic intent into physical hardware IR.
• Connect our agentic flow to physical synthesis tools including OpenRoad, Yosys, ABC, and FusionCompiler.

Minimum qualifications:

• Bachelor’s degree or equivalent practical experience.
• 5 years of experience with software development in C++.
• 3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.

Preferred qualifications:

• Experience with MLIR or CIRCT compiler infrastructures, and writing custom compiler passes or working with High-Level Synthesis.
• Experience with scripting automation, working with tool Application Programming Interfaces (APIs), and sandbox execution.
  
• Experience with proprietary production tools (e.g., FusionCompiler), physical design Power, Performance, and Area (PPA) closure, and open source software (OSS) synthesis toolchains (e.g., Yosys, OpenRoad, or ABC).
• Familiarity with multi-agent design patterns, tool-use loops, and code-generation models.
• Familiarity with containerization, reproducible execution environments, and Continuous Integration and Continuous Delivery (CI/CD) infrastructure.
  
• Familiarity with digital design principles (RTL, Verilog, or SystemVerilog).