Full-Time

Post-Silicon SoC & System-Level Validation Engineer

Deadline 4/28/27
AMD

AMD

10,001+ employees

Designs and sells processors, GPUs, accelerators

No salary listed

Bengaluru, Karnataka, India

In Person

Category
QA & Testing (1)
Required Skills
Palladium
Oscilloscope
Linux/Unix

Get referred to AMD

See people who can refer or advise you

Requirements
  • Experience in pre-silicon and/or post-silicon system-on-chip validation, with strong ownership in post-silicon execution.
  • Strong understanding of system-on-chip architecture and subsystem interactions.
  • Experience validating system-level use cases and customer-driven scenarios.
  • Familiarity with debug tools, system logs, traces, and lab-based validation setups.
  • Strong understanding of system-on-chip boot flows, firmware, and hardware/software interaction.
  • Extensive experience using lab equipment such as oscilloscopes, protocol analyzers, and signal generators.
Responsibilities
  • Own system-on-chip-level post-silicon validation, focusing on interaction between multiple subsystems rather than isolated intellectual property testing.
  • Validate end-to-end system flows involving central processing unit cores, on-chip memories, network-on-chip/interconnect, input/output, power management, and firmware.
  • Ensure correct behavior across boot, runtime, stress, error, and recovery scenarios at the system-on-chip level.
  • Develop validation test cases based on customer use cases, including boot flows, input/output usage, stress, concurrency, and power transitions, and turn them into executable validation plans.
  • Perform deep system-on-chip-level debugging and root-cause analysis to isolate failures across hardware, firmware, and system software boundaries.
  • Use engineering lab equipment, including oscilloscopes, protocol analyzers, and signal generators, to validate and debug functional behavior.
  • Produce test plans, execution reports, failure-analysis summaries, and status updates, and track bugs and issues to closure.
Desired Qualifications
  • Experience with emulation platforms such as Palladium, Protium, and Zebu for pre-silicon or early validation.
  • Exposure to network-on-chip fabrics, power management, clock/reset architecture, and system controllers.
  • Familiarity with system software stacks including bootloaders, Linux, and real-time operating systems and their interaction with silicon.
  • Hands-on experience using artificial intelligence tools.

AMD is a semiconductor company that designs and sells processors, graphics cards, and accelerators for a range of customers, including data centers, AI developers, and enterprises. Its products include Ryzen CPUs for desktops, EPYC CPUs for data centers, and Radeon GPUs for gaming and professional visualization. AMD also offers the ROCm software stack and Instinct accelerators to boost AI and machine learning performance. The company earns revenue from hardware sales, technology licensing, and software that optimizes hardware performance. AMD differentiates itself through a broad portfolio that combines high-performance CPUs, GPUs, and AI accelerators, along with software ecosystems that optimize compute workloads. Its goal is to provide scalable, efficient computing power for gaming, data centers, and AI workloads while pursuing responsible corporate practices.

Company Size

10,001+

Company Stage

IPO

Headquarters

Santa Clara, California

Founded

1969

Get referred to AMD

See people who can refer or advise you

Simplify Jobs

Simplify's Take

What believers are saying

  • Q2 2026 revenue hit $11.5 billion, up 50%, with data center revenue doubling.
  • AMD guided Q3 2026 revenue to $13 billion, implying 41% growth at midpoint.
  • Microsoft, Meta, OpenAI, and Oracle committed to Helios deployments later in 2026.

What critics are saying

  • SpaceX chose Nvidia exclusively on August 2026, underscoring AMD's customer loss risk.
  • AMD's growth depends on a concentrated few: Microsoft, Meta, OpenAI, Oracle, and Anthropic.
  • Gaming revenue fell 31% in Q2 2026; console softness can starve cash for AI.

What makes AMD unique

  • Lisa Su's full-stack strategy bundles EPYC, Instinct, ROCm, and Helios.
  • AMD's open-source ROCm ecosystem reached an inflection point in 2026, widening developer pull.
  • Taalas acquisition on August 6, 2026 adds inference silicon and custom-chip expertise.

Help us improve and share your feedback! Did you find this helpful?

Benefits

Hybrid Work Options

Growth & Insights and Company News

Headcount

6 month growth

24%

1 year growth

24%

2 year growth

19%
Yahoo Finance
Aug 6th, 2026
Nvidia expands AI agent toolkit for chip design as data center revenue hits $75.2B

Nvidia expanded its Agent Toolkit on 26 July, adding PhysicsNeMo and CUDA-X libraries that enable AI agents to handle engineering simulations, physics solvers, and quantum chemistry tasks autonomously. The company is extending its hardware dominance into design software, aiming to lock in customers through workflow integration. Siemens reports 10x faster chip library characterisation using the toolkit, whilst Samsung applies it to lithography and thermal analysis on models with up to 10 billion cells. Nvidia's fiscal first quarter 2027 revenue reached $81.6 billion, with data centre sales accounting for $75.2 billion. Despite strong results, Nvidia shares rose only 17% year-to-date as of 6 August 2026, trailing the S&P 500. Data centre sales comprise 92% of revenue, concentrated amongst hyperscaler customers. Hedge fund ownership increased from 264 to 275 in recent 13F filings.

BetaKit
Aug 6th, 2026
AMD acquires Taalas, Canadian startup that hardwires AI models into custom chips

American semiconductor giant AMD has reached a definitive agreement to acquire Toronto-based Taalas, a startup that aims to hardwire AI models directly onto chips. Financial terms were not disclosed. Taalas was founded in 2023 by former AMD employees and Tenstorrent leaders, including CEO Ljubisa Bajic. The company emerged from stealth in 2024, revealing $50 million in funding from Quiet Capital and Pierre Lamond. The startup uses hard-wired computation to convert AI models into custom silicon, claiming it can launch new chips in two months and produce models a thousand times more efficient than software counterparts. This marks AMD's second acquisition of a Canadian AI chip firm in just over a year, following its purchase of Untether AI's team in 2025.

Yahoo Finance
Aug 6th, 2026
AMD stock drops as SpaceX chooses Nvidia for AI chips despite $11.5B Q2 revenue surge

AMD shares fell Wednesday after SpaceX CEO Elon Musk announced the company would exclusively purchase AI chips from rival Nvidia, citing its Vera Rubin architecture as superior. The drop came despite strong second-quarter results. AMD's revenue jumped 50% year-over-year to $11.5 billion, whilst earnings per share soared 246% to $1.66, beating analyst estimates of $1.61. The company's data centre division led growth, with revenue more than doubling to $6.7 billion, driven by demand for EPYC processors and Instinct GPUs. AMD partners with major AI computing providers including Microsoft, Meta Platforms, Oracle, OpenAI, and Anthropic. AMD projects third-quarter revenue of approximately $13 billion, representing 41% year-over-year growth. However, some investors appear to be seeking faster expansion in the competitive AI chip market.

WhalesBook Private Limited
Aug 5th, 2026
Hark launches AI browser agent following $700M raise at $6B valuation

AI startup Hark has launched Hark Handoff, a browser agent that automates complex online tasks by navigating websites and completing actions without APIs. The tool can order products or book services by analysing website structures. The launch follows a $700 million Series A funding round led by Nvidia, AMD, Intel, Qualcomm, and Salesforce Ventures, valuing the US-based company at $6 billion. Hark is led by Brett Adcock, known for his work with Figure AI and Archer Aviation. The technology predicts specific actions like mouse clicks rather than just generating text. However, Hark faces competition from Google, OpenAI, and Anthropic, alongside potential legal challenges from platforms implementing anti-bot protections and security concerns regarding user credentials and data privacy.

Yahoo Finance
Aug 5th, 2026
AMD shares fall 6% as Musk says SpaceX to use Nvidia AI chips exclusively

AMD shares fell more than 6% on Wednesday after Elon Musk said SpaceX will build exclusively on Nvidia's Blackwell AI platform, calling it the "best architecture". The announcement marked a setback for AMD in the competitive AI accelerator market, despite its strong quarterly results. AMD reported revenue of $11.54 billion for the quarter ended 27 June, beating Wall Street expectations, with adjusted earnings of $1.66 per share. The company guided for approximately $13 billion in current-quarter revenue, above the $12.51 billion analyst consensus. The data centre division delivered record revenue of $6.7 billion, representing 58% of total revenue, up from 42% a year earlier. Chief executive Lisa Su said AI is driving significant demand expansion across all markets.