You will implement and verify new model architectures in a simulator to evaluate hardware requirements before silicon production. You will also collaborate with cross-functional teams to automate the model bring-up process and ensure high-performance inference.
You will design and build the platform layer that enables AI coding agents to drive hardware simulators end-to-end. This involves creating agent workflows, defining API interfaces, and implementing CI guardrails to ensure agent-produced changes are trustworthy and verified.
You will serve as the primary responder for simulation and emulation requests from various internal teams to provide rapid, measured answers. Additionally, you will convert these investigations into reusable assets like calibrated models, experiments, and regression tests.
You will design and deliver performance-estimation tools to help customers understand model throughput and latency on Positron hardware. Additionally, you will model large-scale inference topologies and validate these projections against real hardware measurements.
You will collaborate with chip architects to design and model next-generation AI inference accelerators by quantifying performance tradeoffs and identifying bottlenecks. This involves developing analytical and cycle-level models in Rust to evaluate architectural options and provide actionable design recommendations.
You will design and build simulators for host-to-chip and chip-to-chip communication layers to model complex distributed systems. You will own the software architecture of the simulation stack and ensure it scales to support full-rack simulations for daily CI use.
Define and own the silicon security architecture for an AI accelerator platform, covering secure boot, hardware root of trust, and asset protection. Collaborate across cross-functional teams to integrate security throughout the product lifecycle, from architecture to production deployment.
You will own the end-to-end DFT micro-architecture for AI accelerators, from definition and RTL integration to pre-silicon verification and silicon bring-up. You will also collaborate with physical design and cross-functional teams to ensure high-quality silicon, leveraging AI-enabled tools for productivity.
The engineer will own synthesis, timing convergence, and implementation readiness for key partitions within an AI accelerator roadmap. They will collaborate with cross-functional teams to drive physical-aware optimization and develop scalable synthesis methodologies.
The role involves owning the hardware security architecture for an AI accelerator platform, covering everything from secure boot and root of trust to production deployment. You will also lead threat modeling, security reviews, and cross-functional partnerships to ensure the protection of customer models and data.
You will profile and optimize end-to-end LLM inference performance across hardware-accelerated attention, runtime, and distributed inference architectures. The role involves identifying performance bottlenecks, developing benchmarks, and influencing hardware and software design to improve system efficiency.
The engineer will own the end-to-end FPGA development process, including microarchitecture, RTL design, and lab-based silicon validation. They will also collaborate with cross-functional teams to build prototypes and optimize system performance for AI inference platforms.
You will own the identity and access management, cloud infrastructure, and developer tooling while leading the migration to a secure hybrid-cloud environment. Additionally, you will be responsible for defining security foundations, including threat detection, incident response, and infrastructure as code.
Canada, United States$185K - $250K per year5-10 yrs expOthers
The Senior Mechanical Engineer will own the mechanical, thermal-mechanical, and enclosure design for AI inference platforms from concept through volume production. They will serve as the primary interface for contract manufacturers and lead DFM/DFA reviews to ensure design robustness and cost-effectiveness.
United States$140K - $225K per year5-10 yrs expRecruitment
The Senior Recruiter will own the full-cycle recruiting process for hardware engineering roles, partnering with leaders to define hiring priorities and candidate profiles. They will also build pipelines of passive candidates and utilize AI tools to improve recruiting operations and candidate engagement.
United States$200K - $300K per year10+ yrs expOthers
Lead and grow an engineering team responsible for production platforms, fleet orchestration, and reliability. Establish technical roadmaps and operational standards to ensure scalable, high-availability production systems.
Lead and grow an engineering team responsible for the serving layer, including API fidelity, tokenization, tool calling, and model integration. Establish technical roadmaps and ensure high-performance, reliable production operations for LLM serving systems.
Define the multi-generation platform software architecture for AI inference silicon and ensure seamless integration across firmware, operating systems, and runtime. Lead architecture reviews, drive cross-team technical decisions, and provide reference implementations for critical interfaces.
You will design, implement, and verify IP blocks and subsystems for inference ASICs using SystemVerilog RTL. You will also collaborate with cross-functional teams to resolve design issues, track PPA metrics, and contribute to microarchitecture documentation.
You will lead the microarchitecture and RTL design for complex IP blocks and subsystems, ensuring high-performance silicon outcomes. You will also mentor junior engineers and collaborate across cross-functional teams to drive architectural tradeoffs and signoff processes.
The engineer will own synthesis, timing convergence, and implementation readiness for key partitions within an AI accelerator roadmap. They will collaborate with cross-functional teams to develop synthesis flows, optimize netlists, and drive physical-aware optimization.
You will own the end-to-end DFT implementation for AI accelerators, from micro-architecture definition to silicon bring-up. This involves integrating DFT IP, driving pre-silicon verification, and collaborating with physical design and cross-functional teams to ensure high-quality silicon.
Develop and maintain simulation infrastructure, including analytical performance models and functional simulators for inference systems. Collaborate with hardware and software teams to validate architectural assumptions and ensure simulator consistency with production environments.
The engineer will contribute to the physical implementation of AI accelerators from floorplanning through tapeout. They will drive implementation methodology, timing closure, and cross-functional collaboration to achieve world-class PPA.
The engineer will embed with sub-teams to build and deploy agentic workflows that improve developer productivity across firmware, runtime, and simulation. They will also own the shared skills repository and internal agent tooling to ensure high-quality, evaluated automation within the engineering lifecycle.
United States$200K - $350K per year10+ yrs expProduct
The role involves defining the silicon and systems product line, from accelerator architecture to rack-scale inference systems. You will translate market signals into engineering requirements and manage the product roadmap in collaboration with engineering and go-to-market teams.
United States$200K - $350K per year10+ yrs expProduct
The Technical Product Manager will own the end-to-end planning of the AI inference software stack, translating model advancements into actionable engineering requirements. They will serve as the primary bridge between engineering, go-to-market teams, and ecosystem partners to ensure a competitive and well-documented product roadmap.
United States$150K - $200K per year5-10 yrs expRecruitment
The Senior Recruiter will own full-cycle recruiting for software and systems engineering roles, managing the entire process from intake to offer. They will also partner with engineering leaders to develop effective sourcing strategies and build strong candidate pipelines in a competitive market.
Own the power architecture, estimation, and optimization for AI accelerators across the full development lifecycle. Collaborate cross-functionally to ensure industry-leading performance-per-watt and meet aggressive thermal constraints.
Own the end-to-end physical implementation of AI accelerators from floorplanning through tapeout. Lead implementation methodology and partner with cross-functional teams to achieve world-class PPA and signoff-quality results.