{
  "job_id": "GLjIb6nCF94zVt0aAAAAAA==",
  "job_city": null,
  "job_state": "California",
  "job_title": "AI Engineer (Generative AI & RAG Specialist)",
  "job_salary": null,
  "job_country": "US",
  "job_benefits": null,
  "job_latitude": 36.778261,
  "job_location": "California, United States",
  "job_onet_soc": "15111100",
  "apply_options": [
    {
      "is_direct": false,
      "publisher": "LinkedIn",
      "apply_link": "https://www.linkedin.com/jobs/view/ai-engineer-generative-ai-rag-specialist-at-dimaag-4381061455?utm_campaign=google_jobs_apply&utm_source=google_jobs_apply&utm_medium=organic"
    },
    {
      "is_direct": false,
      "publisher": "Jobright",
      "apply_link": "https://jobright.ai/jobs/info/69ab40727e1fab39d382d902?utm_campaign=google_jobs_apply&utm_source=google_jobs_apply&utm_medium=organic"
    }
  ],
  "employer_logo": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQNxnNsAMK1r5uys0BhHz56I_fqlyC_cLw9uEQ9&s=0",
  "employer_name": "DIMAAG",
  "job_is_remote": false,
  "job_longitude": -119.4179324,
  "job_posted_at": "22 days ago",
  "job_publisher": "LinkedIn",
  "job_apply_link": "https://www.linkedin.com/jobs/view/ai-engineer-generative-ai-rag-specialist-at-dimaag-4381061455?utm_campaign=google_jobs_apply&utm_source=google_jobs_apply&utm_medium=organic",
  "job_highlights": {
    "Qualifications": [
      "Required Skill Set",
      "Core AI: Deep understanding of the Transformer architecture (Attention mechanisms, encoders/decoders)",
      "Frameworks: Proficiency in PyTorch or TensorFlow, and orchestration tools like LangChain",
      "Vector DBs: Hands-on experience with vector similarity search and indexing",
      "Programming: Expert-level Python and experience with API integration",
      "Deployment: Familiarity with cloud AI services (AWS Bedrock, GCP Vertex AI, or Azure AI)",
      "Experience with fine-tuning techniques like LoRA or QLoRA",
      "Contributions to open-source AI projects or research publications",
      "Knowledge of evaluation frameworks for LLMs (e.g., RAGAS or TruLens)"
    ],
    "Responsibilities": [
      "The AI Engineer will focus on building and optimizing state-of-the-art generative AI and retrieval-augmented generation (RAG) models",
      "This individual will design and deploy scalable production systems using Large Language Models (LLMs)",
      "with a focus on building robust Retrieval-Augmented Generation (RAG) pipelines and optimizing transformer-based architectures to solve complex problems",
      "Architect RAG Pipelines: Develop and optimize end-to-end RAG systems for multimodal data, including document parsing, embedding strategies, and vector database management",
      "LLM Implementation: Select, fine-tune, and deploy LLMs (OpenAI, Anthropic, Llama, etc.) using frameworks like LangChain or LlamaIndex",
      "Model Optimization: Work with transformer architectures to improve inference speed and accuracy (quantization, pruning, or prompt engineering)",
      "Data Engineering: Manage unstructured data workflows and high-dimensional vector search (e.g., Pinecone Qdrant, Weaviate, or Milvus)"
    ]
  },
  "job_max_salary": null,
  "job_min_salary": null,
  "job_description": "Company Description\n\nDimaag is a leading design and technology company that specializes in AI solutions across multiple industry verticals including Smart Factory. Established in 2018 and headquartered in Silicon Valley with offices in Osaka, Japan, and Bangalore, India, Dimaag's EV business unit has a strong presence in deployed cutting edge industry solutions through its proprietary ENCORE ecosystem of EV components and charging solutions. Join Dimaag in its mission to create sustainable, high-performance technology for a better future.\n\nRole Description\n\nThis is a full-time, on-site role for an AI Engineer (Generative AI & RAG Specialist) based in Fremont, CA. The AI Engineer will focus on building and optimizing state-of-the-art generative AI and retrieval-augmented generation (RAG) models. This individual will design and deploy scalable production systems using Large Language Models (LLMs). with a focus on building robust Retrieval-Augmented Generation (RAG) pipelines and optimizing transformer-based architectures to solve complex problems.\n\nKey Responsibilities\n\nArchitect RAG Pipelines: Develop and optimize end-to-end RAG systems for multimodal data, including document parsing, embedding strategies, and vector database management.\n\nLLM Implementation: Select, fine-tune, and deploy LLMs (OpenAI, Anthropic, Llama, etc.) using frameworks like LangChain or LlamaIndex.\n\nModel Optimization: Work with transformer architectures to improve inference speed and accuracy (quantization, pruning, or prompt engineering).\n\nData Engineering: Manage unstructured data workflows and high-dimensional vector search (e.g., Pinecone Qdrant, Weaviate, or Milvus).\n\nRequired Skill Set\n\nCore AI: Deep understanding of the Transformer architecture (Attention mechanisms, encoders/decoders).\n\nFrameworks: Proficiency in PyTorch or TensorFlow, and orchestration tools like LangChain.\n\nVector DBs: Hands-on experience with vector similarity search and indexing.\n\nProgramming: Expert-level Python and experience with API integration.\n\nDeployment: Familiarity with cloud AI services (AWS Bedrock, GCP Vertex AI, or Azure AI).\n\nPreferred Qualifications\n\nExperience with fine-tuning techniques like LoRA or QLoRA.\n\nContributions to open-source AI projects or research publications.\n\nKnowledge of evaluation frameworks for LLMs (e.g., RAGAS or TruLens).",
  "job_google_link": "https://www.google.com/search?ibp=htl;jobs&q&htidocid=GLjIb6nCF94zVt0aAAAAAA%3D%3D&hl=en-GB&shndl=37&shmd=H4sIAAAAAAAA_xWNMQrCQBBFsc0RrAYEUZGsCDZaBQ0hhY3BOqxx3KysM8vOIim9g6fwWp7EtfnFg_9e9hllZVFDScYSYoBZhYRBR_tESHwKp6KCxmNntbMS5_B9veHOFxDUoeuBCSpm43C862P0slVKxOVGYnJ0eccPxYQXHlQ6yX9a6XVA73TEdr1ZDbkns5gc6mORSpZgn0I3DmT1Es5kI16hSTKUH6XHyM6sAAAA&shmds=v1_ATWGeePBg_px-R8F447v3zPzy-psuIH7qUM1ORdN2ChzBV-i3Q&source=sh/x/job/li/m1/1#fpstate=tldetail&htivrt=jobs&htiq&htidocid=GLjIb6nCF94zVt0aAAAAAA%3D%3D",
  "employer_website": null,
  "job_onet_job_zone": "5",
  "job_salary_period": null,
  "job_apply_is_direct": false,
  "job_employment_type": "Full–time",
  "job_employment_types": [
    "FULLTIME"
  ],
  "job_posted_at_timestamp": 1772755200,
  "job_posted_at_datetime_utc": "2026-03-06T00:00:00.000Z"
}