---
title: 'Head of Inference Performance Visibility at Etched'
canonical: 'https://feeny.ai/job/head-of-inference-performance-visibility-etched-san-jose-qhxg1v3f47j1'
type: 'job'
last_seen: '2026-11-09'
---

# Head of Inference Performance Visibility at Etched

- **Company:** [Etched](https://feeny.ai/companies/etched)
- **Location:** San Jose, CA
- **Employment:** full-time
- **Work type:** onsite
- **Posted:** 2026-02-19
- **Last confirmed live:** 2026-11-09
- **Apply:** https://jobs.ashbyhq.com/Etched/6c60c888-1b0e-4fc8-b78a-31b9c994a0f4

## Job description

## About Etched

Etched is building hardware for frontier intelligence. We co-design chips, racks, software, and manufacturing to deliver best-in-class throughput and latency across both prefill and decode workloads. Our first products are heavily focused on inference. Backed by hundreds of millions from top-tier investors and staffed by leading engineers, Etched is redefining the infrastructure layer for the fastest growing industry in history.

Job Summary We are hiring a Head of Performance Visibility to define how performance is understood across next-generation AI accelerator systems. Our ML accelerator platform spans custom silicon, supercomputing software, compiler stacks, runtime libraries, and distributed inference environments. Performance at this scale is no longer a device-level question — it is a high-performance distributed system problem. You will define the performance metrics that connect raw hardware signals to distributed workload context, ML cluster dynamics, pod communication patterns, and emergent bottlenecks. This role requires more than telemetry. You will establish new abstractions, structured counter ontologies, cross-layer event correlation frameworks, distributed time-alignment strategies, and scalable reasoning systems operating across nodes, racks, and clusters. Working at the intersection of hardware design, driver architecture, runtime systems, and ML infrastructure, you will shape how these layers expose and consume performance intelligence. This is a foundational role defining not just tooling, but how our platform reasons about efficiency, scalability, and system behavior for years to come.

## Key Responsibilities besides Mentorship and Leadership

System-Level Performance Design

- Define the architectural approach for collecting and structuring telemetry across CPUs, drivers, interconnects, and multiple accelerators
- Design scalable models for correlating performance events across device and host boundaries

Cross-Layer Event Correlation

- Develop mechanisms to align hardware counters, runtime activity, communication phases, and workload semantics across model-layer execution into coherent, actionable insight
- Implement time synchronization and trace-alignment strategies across multi-device systems

Telemetry & Counter Modeling

- Define structured counter taxonomies separating base signals from derived metrics
- Design derived performance models bridging low-level hardware signals and workload-level behavior
- Influence instrumentation strategy for future hardware generations

Distributed Performance Reasoning

- Build tools that identify bottlenecks among multi-accelerator workloads across chips within hosts
- Build cluster-scale performance analysis for distributed inference across data center networks

Tooling & Insight Delivery

- Contribute to analysis engines and developer-facing tooling that transform raw telemetry into intuitive insight
- Shape how performance intelligence is surfaced to engineers debugging large-scale AI systems

You may be a good fit if you have

- Deep experience building complex systems at the intersection of hardware and software
- Personally envisioned and built significant portions of profiling, tracing, or observability systems — not solely defined requirements or product strategy
- Demonstrated ability to translate raw hardware signals into scalable, production-grade telemetry and analysis infrastructure
- Experience correlating time-series events across distributed systems
- Deep systems programming expertise (C++ or Rust), with a track record of shipping low-level infrastructure operating close to hardware or runtime systems
- Experience designing distributed correlation mechanisms, timestamp-alignment strategies, or performance modeling frameworks across multiple devices or hosts
- Experience designing distributed tracing or observability platforms at scale
- Experience with high-performance computing systems and large AI training clusters
- Experience with timestamp synchronization strategies and event alignment in distributed environments
- Experience with hardware counter design and instrumentation strategy
- Experience with performance modeling for large-scale ML workloads
- Experience leading cross-functional architectural initiatives spanning hardware and software teams

## Benefits

- Medical, dental, and vision packages with generous premium coverage
- $500 per month credit for waiving medical benefits
- Housing subsidy of $2.5k per month for those living within walking distance of the office
- Relocation support for those moving to San Jose (Santana Row)
- Various wellness benefits covering fitness, mental health, and more
- Daily lunch and dinner in our office
- Unlimited compute budget subject to ROI justification

## How we’re different

Etched believes in the [Bitter Lesson](http://www.incompleteideas.net/IncIdeas/BitterLesson.html). We are the first inference-focused frontier AI system. Our addressable market is the entirety of inference, unlike many of our competitors.

We are a fully in-person team in San Jose (Santana Row), and greatly value engineering skills. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both and work across disciplines as needed.

## About Etched

## Company Overview
- **One-liner**: Etched designs and manufactures specialized ASICs (application-specific integrated circuits) that are hardwired to run transformer-based AI models, offering an order-of-magnitude improvement in inference cost and energy efficiency over general-purpose GPUs.
- **Entity Type**: Private (Series B / later stage; total raised $800M as of June 2026)
- **Headquarters**: San Jose, California, USA (also has offices in Cupertino, CA; Sacramento, CA; and small presence in Taiwan, Canada, UK, Bulgaria)
- **Founded**: 2022
- **Founders**: Gavin Uberti (CEO), Robert Wachen (President & COO), Chris Zhu (Co-Founder)

## Core Business
- **Primary industry**: AI hardware / semiconductor design / computer hardware manufacturing
- **Target customers**: Frontier AI labs, hyperscalers, and enterprises running large-scale transformer inference workloads (B2B, enterprise)
- **Mission / purpose**: Build hardware for superintelligence – specifically, the world’s most powerful servers for transformer inference.

## Products & Services
- **Sohu Chip (ASIC)**: A transformer-specific ASIC manufactured by TSMC. It burns the transformer architecture directly into silicon, eliminating the overhead of general-purpose GPUs for inference.
- **Frontier Inference Clusters**: Full-stack systems that bundle the Sohu chip with custom-designed racks, networking, and software. Customers place orders for complete systems, not just chips. Etched claims they deliver more tokens per dollar and per watt for dense models, sparse MoEs, diffusion models, and more.
- **Software Stack**: Includes compiler and runtime optimizations built by a team with deep experience (former Apache TVM developer, ex-Google TPU software lead).

## Market Standing
- **Valuation**: $5 billion post-money valuation (as of December 2025 / disclosed June 2026)
- **Key Metric**: $1 billion in contract orders (booked) for its systems; total funding of $800M (including an unannounced $500M round closed Dec 2025 led by Stripes)
- **Notable Investors**: Stripes (lead), VentureTech Alliance, Jane Street, Hudson River Trading, Two Sigma, Ribbit Capital. Angel investors include Andrej Karpathy, Geoffrey Hinton, Fei-Fei Li, Arthur Mensch, Scott Wu, Stanley Druckenmiller, Peter Thiel. Earlier backers: Positive Sum, Primary Venture Partners.
- **Growth Signals**:
  - Headcount: 258 employees (as of mid-2026), up 141% year-over-year
  - 100+ active job postings across engineering, operations, and business functions
  - $500M raise in late 2025; first chip manufactured by TSMC in 2025 and now being tested with customers
  - Talent sources include Google (21), Apple (17), NVIDIA (16), Tesla (11), Intel (10), AMD (5)

## Competitive Advantages
- **Transformer-specific architecture**: Unlike GPUs (which are general-purpose), Etched’s chip is hardwired only for transformer operations, enabling drastically lower cost and latency for today’s dominant AI model architecture.
- **Full-stack system play**: By selling entire inference clusters (chip + rack + software), Etched captures more value and delivers a turnkey solution competitive with NVIDIA’s DGX/HGX systems.
- **Deeply experienced leadership**:
  - CEO Gavin Uberti (Harvard math researcher, AI compiler expert, Apache TVM contributor)
  - President Robert Wachen (co-founded Prod AI incubator; Thiel Fellow)
  - VP of Platform (ex-NVIDIA 22 years, built HGX/DGX systems)
  - VP of Software (ex-Google DeepMind, lead TPU v1–v5 software)
  - Chief Architect Saptadeep Pal (former Auradine co-founder, chiplet expert)
  - VP of Hardware Engineering Ajat Hukkoo (ex-Cypress CTO, shipped >$1B revenue products)

## Strategic Focus
- **Scale manufacturing and customer deliveries**: With the first chip successfully fabricated, the company is now testing production systems and aims to fulfill $1B in pre-orders.
- **Expand engineering talent**: Aggressively hiring across silicon design, validation, infrastructure, optics, and software to support volume ramp.
- **Maintain technological lead**: Continue refining the ASIC for future transformer variants and MoE mixtures while building out a partner ecosystem.

## Why Work Here
- **Mission-driven, high-impact engineering**: “Building the hardware for superintelligence” – the company is solving one of the hardest problems in compute (inference efficiency) with a focused team.
- **Top-tier team and learning environment**: Colleagues from Google, NVIDIA, Apple, Tesla, Broadcom, and Intel; exposure to full-stack chip-to-system design.
- **In-office culture**: All roles are in-office (Cupertino and San Jose, CA). The company emphasizes on-site collaboration for hardware development. Notable perks are not heavily advertised, but compensation is competitive for the AI hardware space (equity-heavy).
- **Growth trajectory**: 141% headcount growth YoY, hundreds of open roles, and a $5B valuation signal strong backing and career acceleration potential.
- **Intellectual challenge**: Work on chip simulation, RTL design, system validation, or software infrastructure for cutting-edge AI inference.

## Sources
1. [etched.com/careers](https://www.etched.com/careers)
2. [builtin.com/company/etched](https://builtin.com/company/etched)
3. [linkedin.com/company/etched-ai](https://www.linkedin.com/company/etched-ai)
4. [cbinsights.com/company/etched](https://www.cbinsights.com/company/etched)
5. [techcrunch.com/2026/06/30/nvidia-competitor-etched-hits-5b-valuation-1b-in-sales-for-ai-chip/](https://techcrunch.com/2026/06/30/nvidia-competitor-etched-hits-5b-valuation-1b-in-sales-for-ai-chip/)

## Other roles at Etched

- [Electrical Engineer - Next Gen Development  (TW)](https://feeny.ai/job/electrical-engineer-next-gen-development-tw-etched-taipei-1p5eavhnv899) — Taipei, Taiwan
- [Infrastructure Engineering & Projects Intern](https://feeny.ai/job/infrastructure-engineering-projects-intern-etched-san-jose-nex7pv255w2v) — San Jose, CA
- [Site Reliability Engineer - Fleet Command & Control](https://feeny.ai/job/site-reliability-engineer-fleet-command-control-etched-san-jose-q5m27r8np5cv) — San Jose, CA
- [IA Research Engineer Intern](https://feeny.ai/job/ia-research-engineer-intern-etched-san-jose-vhnrfnhzby7x) — San Jose, CA
- [Chip Simulation Lead](https://feeny.ai/job/chip-simulation-lead-etched-san-jose-6d9bt85ms6tx) — San Jose, CA
- [Build Engineer](https://feeny.ai/job/build-engineer-etched-san-jose-zmxm6znacgm1) — San Jose, CA
- [Inventory Site Lead (Milpitas)](https://feeny.ai/job/inventory-site-lead-milpitas-etched-san-jose-n83f9gpfm42w) — San Jose, CA
- [Strategic Buyer](https://feeny.ai/job/strategic-buyer-etched-san-jose-e9vh7zjgpwv0) — San Jose, CA
- [People Operations Generalist](https://feeny.ai/job/people-operations-generalist-etched-san-jose-mct9adxz70g2) — San Jose, CA
- [Manufacturing Operations Program Manager (Taiwan)](https://feeny.ai/job/manufacturing-operations-program-manager-taiwan-etched-taoyuan-a7vyayy8zrh7) — Taoyuan, Taiwan