# Himanshu Verma

> Senior GenAI Engineer in Bengaluru, India (6+ yrs). Six years from Java services at TCS, to voice NLP on Samsung Bixby, to multi-agent systems at HDFC. I design agentic workflows with LangGraph and MCP, vectorless RAG, and the LLMOps that keeps them safe in production: gateways, guardrails and evals.

Open to senior GenAI / AI engineering roles, LLM consulting and collaborations on agentic systems. Contact: hello@himanshuverma.dev or LinkedIn (https://www.linkedin.com/in/him0912/). He does not share a phone number.

AI assistants can query this profile live through an MCP server at https://mcp.himanshuverma.dev/mcp (read-only, no sign-in). Setup: https://himanshuverma.dev/ai

## Profile

- [Full profile, projects, posts and Q&A](https://himanshuverma.dev/llms-full.txt): everything below as one Markdown file
- [Profile data (JSON)](https://himanshuverma.dev/profile.json): the same content, structured
- [Website](https://himanshuverma.dev/): career journey, projects with demos and code, 3D world

## Projects

- [Agentic Equity Research Command Center](https://github.com/himanshuverma0912/GenAI-Equity-Research-Command-Center): A multi-agent research workstation. Agents pull metrics from PostgreSQL over MCP, read only the relevant pages of earnings calls via a vectorless PageIndex, score news sentiment, and write an executive briefing with a BUY / HOLD / SELL call.
- [LLM Cost Calculator](https://github.com/himanshuverma0912/ModelCostCalculator): Estimate what an AI product costs to run. Compare inference prices across LLMs, add embeddings and a vector database, and see per-message, per-user and monthly totals, including how much prompt caching saves.
- [GenAI Voice Analytics Library](https://github.com/himanshuverma0912/voice_analytics): Voice analytics building blocks packaged as an importable Python library, so the same transcription and translation logic runs in a web API, an Airflow worker, a batch job or a notebook. Config is injected, and exit codes form a contract orchestrators can branch on.
- [Resume Parser with spaCy NER](https://github.com/himanshuverma0912/Resume-parsing-by-Spacy-NER): Turns unstructured PDF resumes into structured fields. A custom spaCy named-entity model trained on annotated resumes extracts name, designation, companies, skills, college, degree and graduation year.
- [Abstractive Summarization with BART](https://github.com/himanshuverma0912/Abstractive-Text-Summarization-using-Transformers-BART-Model): Paste a news article URL and get a short, readable summary next to the original text. Built on the BART transformer and a dataset of about 40,000 professionally written news summaries.
- [App Review Sentiment Classifier](https://github.com/himanshuverma0912/NLP-Project-on-Text-Processing-and-Classification): End-to-end text processing and a binary classifier for app-store reviews. Compares bag-of-words, binary counts, n-grams and TF-IDF features with logistic regression, and ships a CLI for predictions.

## Blog

- [Vectorless RAG: retrieve by reasoning, not by similarity](https://himanshuverma.dev/blog/vectorless-rag.md): Why "chunk, embed, top-k" struggles on long financial reports, and how a table-of-contents tree that an LLM navigates can find the right pages instead.
- [MCP in 10 minutes: one plug for every tool](https://himanshuverma.dev/blog/mcp-explained.md): What the Model Context Protocol actually standardises: hosts, clients and servers, the three things a server can offer, and what changed in the stateless 2026 spec.

## Recommendations

- [LinkedIn recommendations](https://www.linkedin.com/in/him0912/details/recommendations/): 5 colleagues, including Qurratulain Saleem (Lead AI/ML Engineer, Ascendion), Abhay Kumar (Developer AI, SAP Labs), Sushant Kumar (Lead ML Engineer, Samsung R&D India). Full text in llms-full.txt.

## Interview Q&A

- [Interview Q&A](https://himanshuverma.dev/qa): 10 GenAI interview questions with answers (rag, fine-tuning, llm, decoding, evals, inference, performance, transformers, attention, peft, reliability, guardrails)

## Optional

- [LinkedIn](https://www.linkedin.com/in/him0912/)
- [GitHub](https://github.com/himanshuverma0912)
- [Blog RSS feed](https://himanshuverma.dev/blog/rss.xml)