{
  "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json",
  "basics": {
    "name": "Anuj Sadani",
    "label": "Principal Engineer · AI/ML Systems · Technical Leadership",
    "email": "anuj.k.sadani@gmail.com",
    "phone": "+91 9766880844",
    "url": "https://anujsadani.in",
    "summary": "Engineering leader with 17 years of software development experience, including the last 4 years focused on applied machine learning and generative AI systems. Leads technical direction and people development while staying hands-on with production AI architecture, from model routing and fine-tuning to agent tooling and evaluation. Experience spans document intelligence, distributed systems, cloud platforms, and engineering standards.",
    "location": {
      "city": "Pune",
      "countryCode": "IN",
      "region": "Maharashtra"
    },
    "profiles": [
      {
        "network": "LinkedIn",
        "username": "anujsadani",
        "url": "https://linkedin.com/in/anujsadani"
      },
      {
        "network": "GitHub",
        "username": "asadani",
        "url": "https://github.com/asadani"
      }
    ]
  },
  "work": [
    {
      "name": "Infrrd",
      "position": "Principal Software Development Engineer",
      "location": "Bengaluru, India",
      "startDate": "2021-01",
      "highlights": [
        "Led technical direction and people development for 12+ engineers across three teams, including hiring, mentoring, promotions and team restructuring.",
        "Own the generative AI and machine learning architecture for a document extraction platform processing approximately 1M pages per day, at 1–4¢ per page depending on document class.",
        "Designed and led implementation of a hybrid machine learning and LLM architecture that routes routine workloads through machine learning models and reserves LLM inference for harder cases, reducing operational cost by 30–40% against an LLM only approach.",
        "Designed a Model Context Protocol based agent tooling layer for mortgage document processing, working with underwriting subject matter experts to turn their domain rules into tools that agents call in production.",
        "Fine-tuned small open models for entity extraction from unstructured documents and integrated model based processing into production workflows.",
        "Own and evolve organization wide Python engineering practices, covering security standards, application patterns and code quality across every team that ships Python.",
        "Architected core generative AI and machine learning capabilities behind Infrrd's recognition by Gartner, Everest Group and Deep Analysis."
      ]
    },
    {
      "name": "Delivery Hero",
      "position": "Software Engineer II",
      "location": "Berlin, Germany",
      "startDate": "2020-02",
      "endDate": "2020-12",
      "highlights": [
        "Built and scaled Python and Flask microservices supporting real time order processing within a distributed logistics platform.",
        "Worked with Product Owners and engineering leadership to translate business objectives into technical objectives and key results, roadmaps and delivery plans.",
        "Partnered with data science and business intelligence teams to integrate analytical workflows into production services.",
        "Contributed to operational reliability and incident management using Terraform, Helm, Grafana and New Relic."
      ]
    },
    {
      "name": "NVIDIA",
      "position": "Senior Tools Development Engineer",
      "location": "Pune, India",
      "startDate": "2009-08",
      "endDate": "2020-01",
      "highlights": [
        "Led a team of 8+ engineers building embedded automation frameworks and internal engineering tools supporting graphics processor and system on chip development across multiple product lines.",
        "Owned engineering tools across the full lifecycle, from requirements and architecture through implementation, deployment and long term maintenance.",
        "Drove root cause analysis and corrective action for production issues, and improved engineering productivity through automation first practices.",
        "Introduced a crowdsourcing approach that let engineers outside the core team contribute to internal tooling."
      ]
    }
  ],
  "education": [
    {
      "institution": "Government College of Engineering, Amravati, India",
      "studyType": "Bachelor of Engineering",
      "area": "Information Technology",
      "startDate": "2005",
      "endDate": "2009"
    }
  ],
  "certificates": [
    {
      "name": "Certified ScrumMaster, Scrum Alliance Credential ID 001022708"
    },
    {
      "name": "IBM Enterprise Design Thinking, Co-Creator"
    }
  ],
  "publications": [
    {
      "name": "Tool Attention Is All You Need",
      "summary": "Dynamic tool gating and lazy schema loading for scalable agentic workflows.",
      "url": "https://arxiv.org/abs/2604.21816",
      "releaseDate": "2026"
    },
    {
      "name": "Locale-Conditioned Few-Shot Prompting for On-Device PII Substitution",
      "summary": "Mitigating demonstration regurgitation with small language models.",
      "url": "https://arxiv.org/abs/2605.13538",
      "releaseDate": "2026"
    },
    {
      "name": "The Great Recalibration",
      "summary": "The 2026 pivot from generalist wrappers to application layers and industrialized AI services.",
      "url": "https://dx.doi.org/10.2139/ssrn.6071412",
      "releaseDate": "2026"
    }
  ],
  "skills": [
    {
      "name": "Technical Leadership",
      "keywords": [
        "Technical roadmaps",
        "architecture ownership",
        "hiring",
        "mentoring",
        "performance development",
        "team structure",
        "cross-functional collaboration",
        "engineering standards"
      ]
    },
    {
      "name": "Applied AI Systems",
      "keywords": [
        "Generative AI",
        "Retrieval-Augmented Generation (RAG)",
        "agentic systems",
        "Model Context Protocol (MCP)",
        "LLMs",
        "SLMs",
        "Vision-Language Models (VLMs)",
        "model evaluation",
        "context and prompt engineering"
      ]
    },
    {
      "name": "Agent and LLM Frameworks",
      "keywords": [
        "LangChain",
        "LangGraph",
        "LlamaIndex",
        "CrewAI",
        "PydanticAI",
        "DSPy"
      ]
    },
    {
      "name": "Models, Serving and Routing",
      "keywords": [
        "AWS Bedrock",
        "Amazon SageMaker",
        "vLLM",
        "Ollama",
        "LiteLLM",
        "OpenRouter",
        "multi-provider model routing and fallback"
      ]
    },
    {
      "name": "Machine Learning and Data",
      "keywords": [
        "Fine-tuning (LoRA",
        "QLoRA)",
        "quantization",
        "synthetic data generation",
        "YOLO",
        "OCR",
        "spaCy",
        "Databricks"
      ]
    },
    {
      "name": "Engineering and Platform",
      "keywords": [
        "Python",
        "FastAPI",
        "Flask",
        "microservices",
        "AWS",
        "Docker",
        "Kubernetes",
        "PostgreSQL (RDBMS)",
        "MongoDB (NoSQL)",
        "vector databases"
      ]
    }
  ],
  "patents": [
    {
      "number": "19/375,298",
      "title": "System and Method for Optimizing Queries for Extracting Entities from Documents"
    },
    {
      "number": "19/375,285",
      "title": "System and Method for Optimizing Queries for Extracting Entities and Entity Values from Documents"
    },
    {
      "number": "19/432,186",
      "title": "System and Method for Extraction of Entities from Documents"
    }
  ]
}