# Pranav Dhiran — AI Engineer & Researcher Engineer who ships end-to-end AI/ML systems: training and data pipelines, Python/Go backend services, and agentic infrastructure that runs in production. Owns the pre-training pipeline for a 140M-parameter domain SLM at AIISC (University of South Carolina) — 6.5 GB corpus processing, custom tokenizer, distributed training, automated evaluation harness. LFX '26 Mentee at Hyperledger Cello building the Django/DRF backend, REST/SSE streaming APIs, and an LLM tool-calling agent. Open-source contributor to CNCF's Meshery/MeshKit (Go + React) and author of a published PyPI MCP server. > Machine-readable brief for LLMs and agents. Human site: https://pranavdhiran.me · this file: https://pranavdhiran.me/llms.txt · rendered version: https://pranavdhiran.me/agents ## Identity ### Pranav Dhiran AI Engineer & Researcher · Nagpur, Maharashtra, India Engineer who ships end-to-end AI/ML systems: training and data pipelines, Python/Go backend services, and agentic infrastructure that runs in production. Owns the pre-training pipeline for a 140M-parameter domain SLM at AIISC (University of South Carolina) — 6.5 GB corpus processing, custom tokenizer, distributed training, automated evaluation harness. LFX '26 Mentee at Hyperledger Cello building the Django/DRF backend, REST/SSE streaming APIs, and an LLM tool-calling agent. Open-source contributor to CNCF's Meshery/MeshKit (Go + React) and author of a published PyPI MCP server. - Currently seeking: An internship building production ML/LLM systems. - B.Tech — Electronics & Telecommunication Engineering (Minor in IT) — SGGS Institute of Engineering & Technology, Nanded (2023 – 2027) - Site: https://pranavdhiran.me - Résumé (PDF): https://pranavdhiran.me/Pranav_Dhiran_Resume_1page.pdf - Email: mailto:dhiranpranav72@gmail.com ## Experience _Roles, with the concrete work under each._ ### Research Intern — AIISC, University of South Carolina Apr 2026 – Present The bet: a small model with symbolic constraints can do things a large one can't — not in spite of its size, but because of it. I own the pre-training pipeline that tests the bet. - Own the pre-training pipeline for a 5-person team building an India-focused agriculture SLM — data collection and cleaning through pre-training and evaluation - Built a 140M-parameter Qwen3-style transformer training/eval pipeline (GQA, RoPE, RMSNorm, SwiGLU, factorized embeddings) over a 6.5 GB / 266K-document corpus, with training-health, domain-validation, and safety evaluation frameworks - Built the neurosymbolic layer: BPE tokenizer with AGROVOC entity injection, Z3-based causal KG verification, Triple Transformer Encoder - Built India-Agri-KG — 784 districts, 26 domains, 14,478+ entities, 38,590+ relations — with a 5-stage non-LLM verification layer enforcing source traceability on every triple (unpublished) - Delivered two technical lectures for the IAIRO-affiliated SLM Bootcamp 2026: Vanilla GPT-2 Architecture, and Scaling Laws & Cost Accounting ### LFX Mentee — Hyperledger Cello · Linux Foundation Jun 2026 – Present Fabric has an operations problem: steep learning curve, verbose tooling, too much that shouldn't require an expert. The hard part isn't the LLM — it's knowing which API calls compose into what the operator actually meant. - Building an AI operations copilot for Hyperledger Fabric — natural-language queries to Cello REST APIs through an LLM tool-calling workflow - Implemented the Django/DRF backend and SSE streaming pipeline powering incremental AI responses in the React dashboard - Built a Fabric node-logs API on the agent layer with bounded log retrieval and Docker error handling for AI-assisted node debugging - Developed a multi-party channel invitation workflow end to end: database models, REST APIs, Fabric configuration/signing logic, and dashboard UI ### Open Source Contributor — Meshery — CNCF Sandbox Project Mar 2026 – Jul 2026 The PRs matter less than what you absorb reading other people's production code at scale. - 5+ merged PRs across Meshery's Go backend and React frontend — service-mesh features, UI components, and API integrations - Active in issue triage, code reviews, and contributor discussions under CNCF's open-source workflow ## Selected work _Each has a written case study on this site and source you can read._ ### Medaura - Agentic Pharmacy System Live system · FastAPI · LangChain · LangGraph · ChromaDB · Langfuse · Groq · React Medication errors are an information problem: the data exists, but it is not connected at the moment it matters. - Routing latency under 120ms - Case study: https://pranavdhiran.me/case-studies/medaura - Live system: https://aipharmacyproject-blond.vercel.app ### Small Language Model From Scratch - TinyStories Open source · PyTorch · Python · Custom BPE · AMP · mmap A small transformer built from scratch to understand every layer before trusting higher-level abstractions. - Converged at 2.1 validation loss - Case study: https://pranavdhiran.me/case-studies/tinystories - Source code: https://github.com/Pranav-d33/small_language_model_from_scratch-TinyStories- ### GNU Radio MCP Server - LLM-to-SDR Bridge Open source · Python · FastMCP · ZMQ · XML-RPC · GNU Radio · Pydantic v2 An MCP server that lets language models control live GNU Radio software-defined radio flowgraphs through validated tools. - 13 tools over ZMQ + XML-RPC - Case study: https://pranavdhiran.me/case-studies/gnuradio-mcp - Source code: https://github.com/Pranav-d33/gnuradio-mcp-server ### RF Watch - Open-Source Real-Time RF Spectrum Monitor Open source · Python · GNU Radio · HackRF One · Signal Processing A passive RF spectrum monitor that favors deterministic physical-layer evidence over black-box classification. - Passive spectrum analysis - Case study: https://pranavdhiran.me/case-studies/rf-watch - Source code: https://github.com/Pranav-d33/RFwatch ## Writing ### Why pre-train, not fine-tune? Substack · Ashborn · 2025 Fine-tuning patches behaviour. Pre-training shapes belief. One is a fix; the other is a foundation. - Read: https://ashborn2.substack.com/p/why-pre-train-not-fine-tune?r=5s307l ### How Do You Design a Custom SLM? Substack · Ashborn · Aug 2026 From Qwen3-0.6B to a 133M agricultural language model — not shrinking, but reallocating the parameter budget where it counts. - Read: https://ashborn2.substack.com/p/how-do-you-design-a-custom-slm?r=5s307l ## Talks ### Vanilla GPT-2 Architecture IAIRO SLM++ Bootcamp · PRAMANA Cohort 1 · Session 02 · 2026 A lecture session on the GPT-2 architecture from first principles — how attention, positional encoding, and the decoder stack fit together before any fine-tuning enters the picture. - Watch: https://youtu.be/O-nWMsdMICI?t=3332 ### Evolution of LLM Design Decisions IAIRO SLM++ Bootcamp · PRAMANA Cohort 1 · Session 05 · 2026 A compilation of frontier models case studies — Part 2, Session 05 of PRAMANA: SLM++ Lecture Series. Scaling laws, cost accounting, and how design decisions compound. - Watch: https://youtu.be/IW8s4wQ8-y4?t=4095 ## Skills ### Languages & Frameworks - Python - Go - PyTorch - TensorFlow - Hugging Face Transformers - TRL ### APIs & Protocols - REST - gRPC - GraphQL - OpenAI/Gemini/Ollama APIs - FastMCP - XML-RPC - ZMQ ### LLM Engineering - Instruction fine-tuning - LoRA - PEFT - GRPO - RLHF - INT4/INT8 quantization - Unsloth - LangChain - LangGraph - ChromaDB - FAISS - RAG ### Agentic & Infra - Multi-agent systems - Tool use - Function calling - MCP servers - LangSmith - Langfuse - Docker - Kubernetes ## Recognition ### Awards - Qualified — ETHGlobal 2026 - International Finalist (Top 6) — UWA Hack 2026 - National Finalist — Smart India Hackathon 2024 & 2025 - Regional Qualifier — Nxt Wave × OpenAI Buildathon ## Papers that shaped the work _Not a reading list — each one changed what I thought was possible._ ### ReAct: Synergizing Reasoning and Acting Agents observe before they act. - arXiv: https://arxiv.org/abs/2210.03629 ### Toolformer: Models Teach Themselves to Use Tools The mental model for LLMs using external tools. - arXiv: https://arxiv.org/abs/2302.04761 ### Switch Transformers: Mixture of Experts Modular capacity beats monolithic scaling. - arXiv: https://arxiv.org/abs/2101.03961 ### Group Relative Policy Optimization A foundation for post-training interest. - arXiv: https://arxiv.org/abs/2402.03300 ### Direct Preference Optimization Preference optimization without treating RL as magic. - arXiv: https://arxiv.org/abs/2305.18290 ## Contact ### Cold emails work Reach Pranav Dhiran at dhiranpranav72@gmail.com. - GitHub: https://github.com/Pranav-d33 - LinkedIn: https://linkedin.com/in/prannav-dhiran - Substack: https://ashborn2.substack.com - X: https://x.com/Prannav_ai --- Last generated from site data. Canonical: https://pranavdhiran.me/llms.txt