{
  "@context": "https://schema.org",
  "@type": "ProfilePage",
  "@id": "https://aryanputta.com/recruiter-profile.json",
  "url": "https://aryanputta.com/recruiter-profile.json",
  "name": "Structured profile for Aryan Putta",
  "about": {
    "@type": "Person",
    "@id": "https://aryanputta.com/#person",
    "name": "Aryan Putta",
    "url": "https://aryanputta.com/",
    "email": "aryan.putta@rutgers.edu",
    "sameAs": [
      "https://github.com/aryanputta",
      "https://linkedin.com/in/aryanputta"
    ],
    "affiliation": {
      "@type": "CollegeOrUniversity",
      "name": "Rutgers University"
    },
    "description": "Rutgers computer science and data science student building AI infrastructure research, inference optimization, long-context/KV-cache systems, distributed systems, search infrastructure, GPU systems, model serving, evaluation harnesses, 6G networking, cloud backends, and open-source systems software.",
    "knowsAbout": [
      "AI infrastructure",
      "ML systems",
      "LLM inference",
      "Inference optimization",
      "KV cache",
      "KV-cache optimization",
      "Long-context inference",
      "Positional attention",
      "Distributed systems",
      "Search infrastructure",
      "Information retrieval",
      "GPU systems",
      "CUDA",
      "PyTorch",
      "Model serving",
      "Evaluation harnesses",
      "Benchmark engineering",
      "Cloud infrastructure",
      "Kubernetes",
      "Low-latency systems",
      "Ranking systems",
      "6G networking",
      "AI-native networking",
      "Space systems reliability"
    ],
    "seeks": [
      "Software engineering internships",
      "Off-cycle software engineering internships",
      "Co-ops",
      "AI infrastructure internships",
      "ML systems internships",
      "Member of Technical Staff internships",
      "Systems software internships",
      "GPU systems internships",
      "Research engineering conversations",
      "Research engineering internships",
      "Undergraduate research assistant roles",
      "Early-talent technical programs",
      "Invite-only engineering events",
      "Open-source systems collaborations"
    ]
  },
  "candidateSearchIdentity": [
    "Rutgers computer science and data science",
    "AI infrastructure intern",
    "ML systems intern",
    "software engineering intern",
    "MTS intern",
    "Member of Technical Staff intern",
    "research engineering intern",
    "undergraduate research assistant",
    "inference optimization",
    "KV cache",
    "long-context inference",
    "positional attention",
    "distributed systems",
    "search infrastructure",
    "GPU systems",
    "CUDA",
    "open-source systems PRs"
  ],
  "proofSummary": {
    "mergedOpenSourcePullRequests": 31,
    "mergedPullRequestPhrase": "31 merged open-source pull requests",
    "majorOrganizations": [
      "NVIDIA",
      "IBM",
      "Microsoft",
      "Hugging Face",
      "LinkedIn",
      "FlashAttention",
      "AI Dynamo",
      "Kubernetes",
      "Pulumi"
    ],
    "primaryProofAreas": [
      "AI infrastructure",
      "LLM inference",
      "KV-cache optimization",
      "long-context inference",
      "positional-attention benchmarks",
      "GPU systems",
      "search infrastructure",
      "distributed systems",
      "open-source systems engineering"
    ]
  },
  "researchFocus": [
    {
      "area": "LLM inference optimization",
      "evidence": "EigenKache studies attention-conditioned landmark compression for KV-cache memory pressure in long-context transformer inference."
    },
    {
      "area": "Long-context and positional-attention benchmarks",
      "evidence": "PosCacheBench benchmarks when positional-attention geometry makes far evidence fragile under fixed KV-cache budgets."
    },
    {
      "area": "Search and retrieval infrastructure",
      "evidence": "Switchyard evaluates latency-aware retrieval routing on real Amazon ESCI queries and web-crawl budget allocation."
    },
    {
      "area": "AI-native networking and 6G",
      "evidence": "Research focus includes edge inference, AI-native RAN, network slicing, low-latency systems, and 6G networking constraints."
    },
    {
      "area": "Applied research papers",
      "evidence": "Public paper work includes hybrid satellite telemetry anomaly detection and machine-learning analysis of Bell Labs innovation."
    }
  ],
  "researchSearchIdentity": [
    "AI infrastructure research",
    "research engineering intern",
    "undergraduate research assistant",
    "LLM inference optimization",
    "long-context inference",
    "KV-cache systems",
    "positional-attention benchmark",
    "search infrastructure",
    "information retrieval systems",
    "6G networking research",
    "edge AI inference",
    "satellite telemetry anomaly detection",
    "machine learning research analysis"
  ],
  "bestFitRoles": [
    {
      "role": "research engineering intern",
      "fit": "strong",
      "evidence": [
        "Research focus combines papers, implementation, real baselines, and benchmarked systems",
        "Public artifacts include KVCacheForge-X, RoboFleetOps, EigenKache, PosCacheBench, Switchyard, satellite telemetry anomaly detection, and Bell Labs ML analysis",
        "Primary areas are AI infrastructure research, LLM inference optimization, long-context/KV-cache systems, search infrastructure, and 6G networking"
      ]
    },
    {
      "role": "AI infrastructure intern",
      "fit": "strong",
      "evidence": [
        "31 merged open-source pull requests across infrastructure organizations",
        "KV-cache, LLM inference, model serving, benchmark engineering, and distributed systems project focus",
        "Public repositories include KVCacheForge-X, RoboFleetOps, EigenKache, PosCacheBench, SpaceInferX, ContextFabric, and kvcache-bench"
      ]
    },
    {
      "role": "ML systems intern",
      "fit": "strong",
      "evidence": [
        "Builds and benchmarks inference systems rather than only model demos",
        "Project tags and repository descriptions cover ML systems, LLM inference, evaluation harnesses, and benchmark engineering",
        "Open-source proof includes NVIDIA, IBM, Microsoft, Hugging Face, AI Dynamo, Kubernetes, and Pulumi"
      ]
    },
    {
      "role": "GPU systems intern",
      "fit": "strong",
      "evidence": [
        "Public identity explicitly includes GPU systems and CUDA-adjacent performance work",
        "Work targets inference optimization, KV-cache memory pressure, and low-latency systems",
        "NVIDIA open-source contribution history is listed as public proof"
      ]
    },
    {
      "role": "software engineering intern",
      "fit": "strong",
      "evidence": [
        "31 merged open-source pull requests show code review and production repository workflow",
        "Projects span distributed systems, search infrastructure, cloud infrastructure, and evaluation tooling",
        "Profile is hireable and lists direct contact paths"
      ]
    },
    {
      "role": "Member of Technical Staff intern",
      "fit": "target",
      "evidence": [
        "Systems-first AI infrastructure focus maps to early MTS-style engineering roles",
        "Open-source contribution history shows ability to work in large external codebases",
        "Best matching areas are inference optimization, distributed systems, GPU systems, and model-serving infrastructure"
      ]
    }
  ],
  "publicProof": [
    {
      "type": "open_source",
      "summary": "31 merged open-source pull requests across NVIDIA, IBM, Microsoft, Kubernetes, Pulumi, AWS Labs, DeepSpeed, Hugging Face, LinkedIn, FlashAttention, AI Dynamo, Kubernetes, Pulumi, and related infrastructure repositories.",
      "url": "https://github.com/pulls?q=is%3Apr+author%3Aaryanputta+is%3Amerged+archived%3Afalse"
    },
    {
      "type": "repository",
      "name": "KVCacheForge-X",
      "summary": "KV-cache bottleneck and compute-amplification lab for LLM inference, with TTFT, latency, throughput, HBM stall, GPU busy, tokens/watt, and baseline-delta reporting.",
      "url": "https://github.com/aryanputta/KVCacheForge-X"
    },
    {
      "type": "repository",
      "name": "RoboFleetOps",
      "summary": "AWS-native robotics fleet control plane using Lambda, DynamoDB, SQS, EventBridge, API Gateway, IoT Core, CloudWatch, and CDK CI synthesis.",
      "url": "https://github.com/aryanputta/RoboFleetOps"
    },
    {
      "type": "repository",
      "name": "EigenKache",
      "summary": "KV-cache landmark compression for LLM inference.",
      "url": "https://github.com/aryanputta/EigenKache"
    },
    {
      "type": "repository",
      "name": "PosCacheBench",
      "summary": "Long-context inference benchmark for positional-attention failure modes under KV-cache budget pressure.",
      "url": "https://github.com/aryanputta/PosCacheBench"
    },
    {
      "type": "repository",
      "name": "Switchyard",
      "summary": "SLO-aware retrieval router for web and product search under latency budgets.",
      "url": "https://github.com/aryanputta/Switchyard"
    },
    {
      "type": "repository",
      "name": "NeuroStreamRT",
      "summary": "Real-time EEG inference benchmark with latency-accuracy tradeoffs.",
      "url": "https://github.com/aryanputta/NeuroStreamRT"
    },
    {
      "type": "portfolio",
      "summary": "Portfolio, projects, research, and contact path.",
      "url": "https://aryanputta.com/"
    }
  ],
  "targetRoleFamilies": [
    "Software engineering internships",
    "Off-cycle software engineering internships",
    "Co-ops",
    "AI infrastructure internships",
    "ML systems internships",
    "Research engineering internships",
    "Undergraduate research assistant roles",
    "Systems software internships",
    "GPU systems internships",
    "Cloud infrastructure internships",
    "Platform engineering internships",
    "Research engineering conversations"
  ],
  "contact": {
    "email": "aryan.putta@rutgers.edu",
    "github": "https://github.com/aryanputta",
    "linkedin": "https://linkedin.com/in/aryanputta",
    "portfolio": "https://aryanputta.com/",
    "calendar": "https://calendar.app.google/RsfcmFESA6atnemb8"
  }
}