Skip to content
View arneesh's full-sized avatar
:octocat:
Busy
:octocat:
Busy

Block or report arneesh

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
arneesh/README.md
 █████╗ ██████╗ ███╗   ██╗███████╗███████╗███████╗██╗  ██╗
██╔══██╗██╔══██╗████╗  ██║██╔════╝██╔════╝██╔════╝██║  ██║
███████║██████╔╝██╔██╗ ██║█████╗  █████╗  ███████╗███████║
██╔══██║██╔══██╗██║╚██╗██║██╔══╝  ██╔══╝  ╚════██║██╔══██║
██║  ██║██║  ██║██║ ╚████║███████╗███████╗███████║██║  ██║
╚═╝  ╚═╝╚═╝  ╚═╝╚═╝  ╚═══╝╚══════╝╚══════╝╚══════╝╚═╝  ╚═╝

Typing SVG


About me

Serial Founding Engineer. Built and worked at multiple fast paced startups.

I build products from scratch, full stack, AI-native, production-grade. I thrive in high pressure environments. Fast paced environments is where I work best in.

  •   Currently deep in agentic systems, MCP, and fine-tuning
  •   Building at the intersection of AI + real products


const arneesh = {
  languages:  ["TypeScript", "Python", "JavaScript", "Swift"],

  fullStack: {
    frontend:  ["React", "Next.js", "Vue", "Tailwind", "SwiftUI"],
    backend:   ["Node.js", "Express", "FastAPI", "GraphQL", "Pydantic"],
  },

  aiAndLLMs: {
    techniques:    ["RAG", "LLM Fine-Tuning", "LoRA", "QLoRA", "PEFT",
                    "Prompt Engineering", "NER", "Semantic Search",
                    "Embeddings", "Multimodal AI", "Eval Pipelines"],
    frameworks:    ["LangChain", "LangGraph", "LlamaIndex", "LangSmith",
                    "Hugging Face", "Vertex AI", "Ollama", "vLLM"],
    agents:        ["OpenAI Agents", "CrewAI", "AutoGen", "MCP"],
    models:        ["GPT-4o", "Claude 3.5", "Llama 3", "Gemini", "Mistral"],
    vectorDbs:     ["ChromaDB", "Pinecone", "pgvector"],
  },

  infrastructure: {
    cloud:     ["GCP", "AWS"],
    devops:    ["Kubernetes", "Docker", "CI/CD", "Serverless", "Pub/Sub", "Kafka"],
    databases: ["PostgreSQL", "BigQuery", "MongoDB", "Redis",
                "Elasticsearch", "Firestore", "ChromaDB", "Pinecone"],
    tooling:   ["Cursor", "Claude Code", "Turborepo", "Monorepo"],
  }
};

What I actually build

AI Systems

Production RAG pipelines, multi-agent orchestration, LLM fine-tuning with LoRA / QLoRA / PEFT, conversational agents, semantic search, and eval frameworks.

Full Stack Products

End-to-end ownership from DB schema to deployed UI. React frontends, Node.js / Python backends, serverless infra, payments, webhooks, integrations.

Platform & Infra

Multi-tenant SaaS, Kubernetes clusters, distributed data pipelines, Elasticsearch at scale, real-time systems, billing engines built for enterprise SLAs.


Tech Stack

Languages & Frameworks

TypeScript Python React Next.js Node.js FastAPI

AI & ML

OpenAI Anthropic Hugging Face LangChain PyTorch

Databases & Search

PostgreSQL Redis Elasticsearch MongoDB BigQuery

Cloud & DevOps

Google Cloud AWS Docker Kubernetes


Writing

I write about AI engineering, system design, and building products on Medium, Turbomem. I also write technical blogs and content for companies.


Connect

LinkedIn Medium Twitter


Open to the right conversations, building something new or making something better.

Pinned Loading

  1. turbomem/turbomem turbomem/turbomem Public

    Embedded memory for TypeScript agents.

    TypeScript 6

  2. contextcrunch contextcrunch Public

    Compress long-form logs and text into schema-valid JSON capsules for AI agents. Cited evidence, massive token reduction, and optional smart LLM refinement only when it helps.

    TypeScript 2

  3. openai-finetuning-framework openai-finetuning-framework Public

    A generic Python framework for fine-tuning OpenAI chat models on arbitrary tasks.

    Python 2

  4. qlora-finetuning-framework qlora-finetuning-framework Public

    QLoRA finetuning framework

    Python 2

  5. turborepo-vue-starter turborepo-vue-starter Public

    Turborepo, Vue 3 starter - monorepo

    Vue 40 10

  6. agent-protocols agent-protocols Public

    Structured engineering protocols that make AI coding agents work like senior engineers.

    Shell 1