AI Infrastructure & Experience Engineer

{
  "content_hash": "d438b61818e684d8fd2d68161ad061950c5c8f770856a86812c07b744d062a82",
  "source_hash": "54be4e3afc6aba1c7ebc383af1c11354d413222c716564fe49953d69f158aefb",
  "last_changed_at": "2026-06-06T10:34:58.083Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Mountain View, CA",
    "city": "Mountain View",
    "region": "CA",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.9
  },
  "salary_max": null,
  "salary_min": 70,
  "inferred_at": "2026-06-06T19:21:46.150Z",
  "launch_scope": {
    "reason": "jazzhr_production_catalog",
    "included": true,
    "location": {
      "raw": "Mountain View, CA",
      "city": "Mountain View",
      "region": "CA",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.9
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": null,
  "salary_period": "hour",
  "workplace_type": "on_site",
  "salary_currency": "USD"
}

{}

{
  "detail": {
    "url": "https://focuskpi.applytojob.com/apply/jobs/details/kRKV4324ft?&",
    "heading": "AI Infrastructure & Experience Engineer",
    "html_title": "JazzHR » Job Listings",
    "canonical_url": "https://focuskpi.applytojob.com/apply/kRKV4324ft/AI-Infrastructure-Experience-Engineer",
    "description_html": "<p>FocusKPI is seeking an <strong>AI Infrastructure & Experience Engineer </strong>to join one of our clients, a high-tech SaaS company. </p><p><strong><u>Work Location:</u> </strong>Mountain View, CA (Onsite role, 5 days/week onsite)<br><u><strong>Duration:</strong></u> 4-month contract <br><strong><u>Pay Range:</u> </strong>$70 - 79/hr<br><br><u><strong>**No C2C resumes are considered**</strong></u><br> </p><p><u><strong>Position Responsibilities:</strong></u></p><ul><li><strong>Inference Optimization:</strong> Deploy and tune multiple LLMs and generative multimodal models on local inference hardware. Optimize performance metrics (TTFT, tokens/sec) via model quantization, caching strategies, and architecture-specific adjustments.</li><li><strong>Systems Engineering & CUDA:</strong> Leverage deep knowledge of the CUDA environment to build custom kernels, ensuring maximum utilization of the low-cost GPU compute.</li><li><strong>Orchestration & Integration:</strong> Seamlessly bridge inference backends with orchestration layers (LiteLLM, Ollama, etc.) and frontends like OpenWebUI.</li><li><strong>Rapid Prototyping:</strong> Build functional, high-fidelity demos showcasing model memory capabilities, agentic workflows, and context-aware web search.</li><li><strong>Peripheral Connectivity:</strong> Implement communication protocols to bridge local AI compute with peripheral devices, including smart TVs, household appliances, and XR hardware.</li></ul><u><strong>Requirements/Technical qualifications:</strong></u><ul><li>Recent experience in<strong> model optimization is required</strong></li><li><strong>Hardware & Compute:</strong> Proven experience with NVIDIA ecosystems and ARM64 architecture.</li><li><strong>Systems Programming:</strong> Advanced proficiency in C++, Python, and Rust. Deep familiarity with CUDA and the ability to author/debug custom CUDA kernels for compute-intensive tasks.</li><li><strong>AI/ML Frameworks:</strong> Extensive experience with modern inference engines (llama.cpp, TensorRT-LLM, Ollama) and orchestration frameworks (LiteLLM).</li><li><strong>Software Engineering:</strong> Robust understanding of asynchronous programming (FastAPI), containerization (Docker/Kubernetes), sandbox environments, and API design for low-latency communication.</li><li><strong>Full-Stack Prototyping:</strong> Ability to quickly spin up modern frontend UIs (React, Next.js, or similar) to present AI-driven intelligence to end users.</li><li><strong>Communication Protocols:</strong> Familiarity with WebSockets, gRPC, and REST for device-to-device communication in a local network environment.</li><li><strong>Overall Mandatory skills required:</strong> Model optimization recent exparience, Interference Optimization, NVIDIA ecosystems, Custom CUDA Kernel Development, ARM64 architecture, Python</li></ul><u><strong>Ideal Candidate Profile:</strong></u><ul><li><strong>A minimum of 3 years of relevant industry experience is required</strong></li><li><strong>The \"Builder\" Mindset:</strong> You are energized by the prospect of building proofs-of-concept in days rather than months. You thrive in environments where speed and creativity are paramount.</li><li><strong>Problem Solver:</strong> You approach unsolved, messy engineering challenges with enthusiasm rather than trepidation.</li><li><strong>Architectural Vision:</strong> You see the \"big picture\" of how AI becomes part of consumers' daily lives, not just how the model generates text.</li><li><strong>Agile & Adaptable:</strong> You are comfortable working in a fast-paced environment where priorities shift based on the results of rapid experimentation.</li><li>Degree in<strong> Computer Science, Machine Learning, or Artificial Intelligence Specialization </strong>preferred, but not required</li></ul><br><u><strong>**No C2C resumes are considered**</strong></u><br> <p>Thank you!</p><p>FocusKPI Hiring Team</p><p>Founded in 2010, FocusKPI, Inc. (FocusKPI) is a data science and technology firm specializing in predictive analytics practice and methodologies. FocusKPI is a US company headquartered in Silicon Valley, California, with an East Coast office in Boston, Massachusetts.</p><p> </p>\n\n<p><strong>NOTICE: </strong>Please be aware of fraudulent emails regarding job postings, job offers and fake checks. FocusKPI's recruiting team will strictly reach out via @focuskpi.com email domain. If you have received fraudulent emails now or in the past, please report it to <a href=\\\"https://reportfraud.ftc.gov/\\\">https://reportfraud.ftc.gov/</a> .<br />\nThe domain @focuskpijobs.com is fraudulent and not related to FocusKPI. Please do not not reply or communicate to anyone with @focuskpijobs.com.</p>",
    "description_text": "FocusKPI is seeking an  AI Infrastructure & Experience Engineer  to join one of our clients, a high-tech SaaS company.\n Work Location:   Mountain View, CA (Onsite role, 5 days/week onsite)\n Duration:  4-month contract\n Pay Range:   $70 - 79/hr\n **No C2C resumes are considered**\n Position Responsibilities:\n Inference Optimization:  Deploy and tune multiple LLMs and generative multimodal models on local inference hardware. Optimize performance metrics (TTFT, tokens/sec) via model quantization, caching strategies, and architecture-specific adjustments.\n Systems Engineering & CUDA:  Leverage deep knowledge of the CUDA environment to build custom kernels, ensuring maximum utilization of the low-cost GPU compute.\n Orchestration & Integration:  Seamlessly bridge inference backends with orchestration layers (LiteLLM, Ollama, etc.) and frontends like OpenWebUI.\n Rapid Prototyping:  Build functional, high-fidelity demos showcasing model memory capabilities, agentic workflows, and context-aware web search.\n Peripheral Connectivity:  Implement communication protocols to bridge local AI compute with peripheral devices, including smart TVs, household appliances, and XR hardware.\n Requirements/Technical qualifications: Recent experience in model optimization is required\n Hardware & Compute:  Proven experience with NVIDIA ecosystems and ARM64 architecture.\n Systems Programming:  Advanced proficiency in C++, Python, and Rust. Deep familiarity with CUDA and the ability to author/debug custom CUDA kernels for compute-intensive tasks.\n AI/ML Frameworks:  Extensive experience with modern inference engines (llama.cpp, TensorRT-LLM, Ollama) and orchestration frameworks (LiteLLM).\n Software Engineering:  Robust understanding of asynchronous programming (FastAPI), containerization (Docker/Kubernetes), sandbox environments, and API design for low-latency communication.\n Full-Stack Prototyping:  Ability to quickly spin up modern frontend UIs (React, Next.js, or similar) to present AI-driven intelligence to end users.\n Communication Protocols:  Familiarity with WebSockets, gRPC, and REST for device-to-device communication in a local network environment.\n Overall Mandatory skills required:  Model optimization recent exparience, Interference Optimization, NVIDIA ecosystems, Custom CUDA Kernel Development, ARM64 architecture, Python\n Ideal Candidate Profile: A minimum of 3 years of relevant industry experience is required\n The \"Builder\" Mindset:  You are energized by the prospect of building proofs-of-concept in days rather than months. You thrive in environments where speed and creativity are paramount.\n Problem Solver:  You approach unsolved, messy engineering challenges with enthusiasm rather than trepidation.\n Architectural Vision:  You see the \"big picture\" of how AI becomes part of consumers' daily lives, not just how the model generates text.\n Agile & Adaptable:  You are comfortable working in a fast-paced environment where priorities shift based on the results of rapid experimentation.\n Degree in Computer Science, Machine Learning, or Artificial Intelligence Specialization preferred, but not required\n **No C2C resumes are considered**\n  Thank you!\n FocusKPI Hiring Team\n Founded in 2010, FocusKPI, Inc. (FocusKPI) is a data science and technology firm specializing in predictive analytics practice and methodologies. FocusKPI is a US company headquartered in Silicon Valley, California, with an East Coast office in Boston, Massachusetts.\n NOTICE: Please be aware of fraudulent emails regarding job postings, job offers and fake checks. FocusKPI's recruiting team will strictly reach out via @focuskpi.com email domain. If you have received fraudulent emails now or in the past, please report it to https://reportfraud.ftc.gov/ .\nThe domain @focuskpijobs.com is fraudulent and not related to FocusKPI. Please do not not reply or communicate to anyone with @focuskpijobs.com.",
    "jsonld_jobposting": {
      "url": "https://focuskpi.applytojob.com/apply/kRKV4324ft/AI-Infrastructure-Experience-Engineer",
      "@type": "JobPosting",
      "title": "AI Infrastructure & Experience Engineer",
      "@context": "http://schema.org/",
      "datePosted": "2026-06-05",
      "description": "<p>FocusKPI is seeking an <strong>AI Infrastructure & Experience Engineer </strong>to join one of our clients, a high-tech SaaS company. </p><p><strong><u>Work Location:</u> </strong>Mountain View, CA (Onsite role, 5 days/week onsite)<br><u><strong>Duration:</strong></u> 4-month contract <br><strong><u>Pay Range:</u> </strong>$70 - 79/hr<br><br><u><strong>**No C2C resumes are considered**</strong></u><br> </p><p><u><strong>Position Responsibilities:</strong></u></p><ul><li><strong>Inference Optimization:</strong> Deploy and tune multiple LLMs and generative multimodal models on local inference hardware. Optimize performance metrics (TTFT, tokens/sec) via model quantization, caching strategies, and architecture-specific adjustments.</li><li><strong>Systems Engineering & CUDA:</strong> Leverage deep knowledge of the CUDA environment to build custom kernels, ensuring maximum utilization of the low-cost GPU compute.</li><li><strong>Orchestration & Integration:</strong> Seamlessly bridge inference backends with orchestration layers (LiteLLM, Ollama, etc.) and frontends like OpenWebUI.</li><li><strong>Rapid Prototyping:</strong> Build functional, high-fidelity demos showcasing model memory capabilities, agentic workflows, and context-aware web search.</li><li><strong>Peripheral Connectivity:</strong> Implement communication protocols to bridge local AI compute with peripheral devices, including smart TVs, household appliances, and XR hardware.</li></ul><u><strong>Requirements/Technical qualifications:</strong></u><ul><li>Recent experience in<strong> model optimization is required</strong></li><li><strong>Hardware & Compute:</strong> Proven experience with NVIDIA ecosystems and ARM64 architecture.</li><li><strong>Systems Programming:</strong> Advanced proficiency in C++, Python, and Rust. Deep familiarity with CUDA and the ability to author/debug custom CUDA kernels for compute-intensive tasks.</li><li><strong>AI/ML Frameworks:</strong> Extensive experience with modern inference engines (llama.cpp, TensorRT-LLM, Ollama) and orchestration frameworks (LiteLLM).</li><li><strong>Software Engineering:</strong> Robust understanding of asynchronous programming (FastAPI), containerization (Docker/Kubernetes), sandbox environments, and API design for low-latency communication.</li><li><strong>Full-Stack Prototyping:</strong> Ability to quickly spin up modern frontend UIs (React, Next.js, or similar) to present AI-driven intelligence to end users.</li><li><strong>Communication Protocols:</strong> Familiarity with WebSockets, gRPC, and REST for device-to-device communication in a local network environment.</li><li><strong>Overall Mandatory skills required:</strong> Model optimization recent exparience, Interference Optimization, NVIDIA ecosystems, Custom CUDA Kernel Development, ARM64 architecture, Python</li></ul><u><strong>Ideal Candidate Profile:</strong></u><ul><li><strong>A minimum of 3 years of relevant industry experience is required</strong></li><li><strong>The \"Builder\" Mindset:</strong> You are energized by the prospect of building proofs-of-concept in days rather than months. You thrive in environments where speed and creativity are paramount.</li><li><strong>Problem Solver:</strong> You approach unsolved, messy engineering challenges with enthusiasm rather than trepidation.</li><li><strong>Architectural Vision:</strong> You see the \"big picture\" of how AI becomes part of consumers' daily lives, not just how the model generates text.</li><li><strong>Agile & Adaptable:</strong> You are comfortable working in a fast-paced environment where priorities shift based on the results of rapid experimentation.</li><li>Degree in<strong> Computer Science, Machine Learning, or Artificial Intelligence Specialization </strong>preferred, but not required</li></ul><br><u><strong>**No C2C resumes are considered**</strong></u><br> <p>Thank you!</p><p>FocusKPI Hiring Team</p><p>Founded in 2010, FocusKPI, Inc. (FocusKPI) is a data science and technology firm specializing in predictive analytics practice and methodologies. FocusKPI is a US company headquartered in Silicon Valley, California, with an East Coast office in Boston, Massachusetts.</p><p> </p>\n\n<p><strong>NOTICE: </strong>Please be aware of fraudulent emails regarding job postings, job offers and fake checks. FocusKPI's recruiting team will strictly reach out via @focuskpi.com email domain. If you have received fraudulent emails now or in the past, please report it to <a href=\\\"https://reportfraud.ftc.gov/\\\">https://reportfraud.ftc.gov/</a> .<br />\nThe domain @focuskpijobs.com is fraudulent and not related to FocusKPI. Please do not not reply or communicate to anyone with @focuskpijobs.com.</p>",
      "jobLocation": {
        "@type": "Place",
        "address": {
          "@type": "PostalAddress",
          "postalCode": "",
          "addressRegion": "CA",
          "addressLocality": "Mountain View"
        }
      },
      "validThrough": "2026-09-03",
      "uniqueJobCode": "job_20260605202412_7AMWASQWIWZXENMD",
      "employmentType": "CONTRACTOR",
      "hiringOrganization": {
        "logo": "https://s3.amazonaws.com/resumator/customer_20140207234534_9FZU4QPSBXKUCYMT/logos/20240613191817_HORIZONTAL_LOGO.jpg",
        "name": "FocusKPI Inc.",
        "@type": "Organization",
        "sameAs": "http://focuskpi.com"
      },
      "experienceRequirements": "Mid Level"
    }
  },
  "list_job": {
    "id": "kRKV4324ft",
    "title": "AI Infrastructure & Experience Engineer",
    "detailUrl": "https://focuskpi.applytojob.com/apply/jobs/details/kRKV4324ft?&"
  },
  "detail_errors": []
}