ML and AI Knowledge Systems Engineer

AMD
San Jose
Workplace: HybridFull timeFunction: IT Operations (Systems/Network Admin)Skills: ["Technical leadership","Mentoring","Communication","Technical decision-making","Systems engineering"]

Lead GoldenEye’s ML architecture for retrieval, ranking, and citation-grounded answers across GPU design knowledge (RTL, microarchitecture, verification artifacts, Confluence, and JIRA). Scale a working prototype into an authoritative, production system for thousands of engineers by defining embeddings/chunking, hybrid retrieval, evaluation frameworks, and hallucination-reduction methods. Partner across hardware, software, infrastructure, and security while mentoring engineers and optimizing inference on AMD Instinct GPUs.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
AMD
AMD
2 days ago

ML and AI Knowledge Systems Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Lead GoldenEye’s ML architecture for retrieval, ranking, and citation-grounded answers across GPU design knowledge (RTL, microarchitecture, verification artifacts, Confluence, and JIRA). Scale a working prototype into an authoritative, production system for thousands of engineers by defining embeddings/chunking, hybrid retrieval, evaluation frameworks, and hallucination-reduction methods. Partner across hardware, software, infrastructure, and security while mentoring engineers and optimizing inference on AMD Instinct GPUs.
Location: San Jose
Workplace: Hybrid
Employment Type: Full time
Job Function: IT Operations (Systems/Network Admin)
Seniority: Mid level

Key Responsibilities

  • •Own the architecture for embeddings, chunking, hybrid retrieval, reranking, multi-query planning, and reciprocal-rank fusion.
  • •Build retrieval workflows across specifications, RTL, verification artifacts, wikis, and issue trackers.
  • •Reduce hallucinations using grounded generation, citation enforcement, source validation, and conflict resolution.
  • •Define source-authority and freshness policies, and ensure retrieval/caching/answer generation follow per-user access controls.
  • •Create and drive evaluation frameworks for retrieval relevance, answer correctness, citation faithfulness, latency, cost, and regressions; optimize workloads on AMD Instinct GPUs; mentor engineers and communicate technical decisions.

Key Requirements

  • •Deep relevant experience building production ML, search, ranking, or information-retrieval systems.
  • •Hands-on experience with RAG, embeddings, vector and keyword search, reranking, chunking, and retrieval evaluation.
  • •Practical experience with LLM prompting, structured generation, tool calling, evaluation, and hallucination reduction.
  • •Experience designing ML evaluation datasets, metrics, experiments, and regression tests.
  • •Strong software and systems engineering skills (APIs, asynchronous processing, observability, production operations).
Experience:AIInformation retrievalSearchRAGLLM
Skills:Technical leadershipMentoringCommunicationTechnical decision-makingSystems engineering
Languages:En-us
Tech Stack:RAGEmbeddingsVector searchKeyword searchRerankingChunkingHybrid retrievalReciprocal-rank fusionLLM promptingStructured generationTool callingVLLMMCPCoding agentsAPIsAsynchronous processingObservabilityConfluenceJIRARTL

Company Brief

AMD
Designs and produces semiconductor products including CPUs, GPUs, and adaptive SoCs for consumer, enterprise, and embedded markets, competing across PCs, data centers, and gaming industries.
Industry: Electronics Manufacturing
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Santa Clara, United States
Founded: 1969
Glassdoor
Glassdoor: 3.9
WebsiteLinkedIn