Skip to content
View irfanalidv's full-sized avatar

Organizations

@brainsfeed @re-sources-io

Block or report irfanalidv

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
irfanalidv/README.md

Hi, I'm Irfan

Senior AI engineer building production LLM systems — RAG pipelines, agent orchestration, multi-provider LLM infrastructure, and voice AI on telephony. Based in India, working remote.

I run DataCortex IQ, my AI engineering studio. Currently open to long-term embedded engagements (6–12+ months) with growth-stage AI/LLM teams — engaged through DataCortex IQ.

Previously the founding AI engineer at Kuration AI (Hong Kong) and the first AI hire at Schneider Electric / Luminous Power Technologies (India), reporting to the CTO.

📫 Reach me: [email protected] · LinkedIn · datacortex.in


What I work on

LLMs · RAG · Agents · Voice AI · Multi-provider orchestration

Python · FastAPI · LangChain · LangGraph · DSPy · LlamaIndex · OpenAI · Anthropic · Google · Groq · PostgreSQL · pgvector · Bolna · Twilio


Shipped products

  • Reflecta — a voice-first AI wellness app you can call on the phone. Voice AI · Telephony · LLM analysis · Production. Solo build, end-to-end.
  • Stacksift — a B2B domain product analyzer using DSPy and OpenAI for LLM-based classification, categorisation, and structured extraction over web data.

Open-source Python libraries

  • AgentEnsemble — multi-agent orchestration. ReAct, Swarm, Pipeline, Debate, WorkflowGraph patterns
  • ragfallback — resilient retrieval: query rewriting, confidence scoring, fallback strategies, retry logic
  • RAGNav — navigation-first RAG for long documents. Routes queries, follows cross-references
  • AgentCare — voice AI for healthcare. Call intake, structured extraction, appointment orchestration
  • scrapeflow-py — Playwright-based scraping with LLM extraction, hybrid selectors, anti-detection
  • AskPandas — natural-language queries on CSV data using local LLMs. No API keys, no cloud
  • lingo-nlp-toolkit — lightweight NLP utilities bridging traditional pipelines and transformer workflows
  • PyroChain — agentic feature engineering. PyTorch + LangChain agents for multimodal extraction
  • toxic-comment-classifier — deep-learning toxicity detection with per-category scoring

All libraries are on my PyPI profile.


Publications

  • Mental Health AI on MentalChat16K — IJAINN, Dec 2025 · DOI
  • Neural-Symbolic Topic Evolution on Yelp Reviews — IJAINN, Oct 2025 · DOI

Reliability over hype · Systems over scripts · Maintainability over short-term hacks.

Pinned Loading

  1. ragfallback ragfallback Public

    ragfallback is a Python library that prevents silent RAG failures — chunk quality, retrieval fallback, adaptive querying, and answer evaluation in one package.

    Python 2

  2. AgentEnsemble AgentEnsemble Public

    AgentEnsemble is a Production-ready multi-agent orchestration for Python. ReAct, Swarm, Pipeline, Debate, Router, Planner, WorkflowGraph. Observability, cost tracking, human-in-loop. Structured out…

    Python 1

  3. AskPandas AskPandas Public

    AI-powered data engineering and analytics assistant for querying CSV data using natural language—locally and intelligently

    Python 1

  4. scrapeflow-py scrapeflow-py Public

    Production-ready web scraping engine on Playwright. LLM extraction, hybrid selectors, session persistence, rate limiting, anti-detection.

    Python 1

  5. AgentCare AgentCare Public

    Python framework for voice-AI workflows: healthcare front-desk booking, care coordination, follow-up, and workplace burnout check-ins.

    Python 1

  6. RAGNav RAGNav Public

    RAGNav is a Hybrid RAG retrieval — BM25 + embeddings + document graph. Runs fully offline. SQuAD R@3: 0.956, zero API calls.

    Python 1