Core Software Engineering at Etched.ai

San Jose, California, United States

Apply Now

Not SpecifiedCompensation

Mid-level (3 to 4 years), Senior (5 to 8 years)Experience Level

Full TimeJob Type

UnknownVisa

Artificial Intelligence, Semiconductors, HardwareIndustries

Requirements

Talented software engineering background with hunger to contribute across many systems
Obsession with building robust software for developers, designing systems that harness massive compute, and solving unique large-scale problems
Ability to design and scale distributed systems for development and deployment pipelines
Experience or strong interest in orchestrating fleets of machines across hybrid superclusters
Capability to work hands-on with on-prem systems (infrastructure experience not strictly required)

Responsibilities

Build reliable, high-performance systems and core frameworks/workflows to enable fast engineering iteration on hybrid superclusters, orchestrating thousands of machines for continuous simulation, verification, and chip building
Engineer fault-tolerant, high-throughput CI pipelines for backend processes including simulation, synthesis, CDC, performance regressions, and nightly flows
Scale bare-metal superclusters and hybrid infrastructure, optimizing CPU/memory topology, EDA workloads, and core saturation across on-prem racks and clouds
Design high-quality tools, interfaces, dev workflows, and execution engines for EDA processes to make them reproducible, fast, and user-friendly
Develop representative projects such as: fully automated correctness-first CI systems; massively parallel workload schedulers for compute-heavy tasks; on-demand, GPU-backed, reproducible dev environments with zero-downtime and fault tolerance

Skills

Distributed Systems

High-Performance Systems

Supercomputing

Hybrid Superclusters

Simulation

Orchestration

Software Frameworks

Workflows

Compute Infrastructure

Systems Engineering

Etched.ai

Develops servers for transformer inference

About Etched.ai

The company specializes in developing powerful servers for transformer inference, utilizing transformer architecture integrated into their chips to achieve highly efficient and advanced technology. The main technologies used in the product are transformer architecture and advanced chip integration.

Cupertino, CA, USAHeadquarters

2022Year Founded

$5.4MTotal Funding

SEEDCompany Stage

HardwareIndustries

11-50Employees