AI Engineer · Fairfax, VA

Naga VenkataSai Chennu

Building LLM agents, tool calling, fine-tuning, model evaluation, RAG

I build LLM systems end to end: agents that call tools to finish real tasks, fine-tuned models that keep what they already knew, and the evaluations that prove both work.

peer-reviewed papers
5
citations
50+
chart images evaluated
6,000
AI certifications
3
Experience

Where I’ve shipped

From a pre-launch fintech startup to university research: LLM systems that do real work, measured by real numbers.

May 2026 – PresentRemotesmartremit.ai ↗

SmartRemit

Co-founder & Lead Engineer

Sole engineer on a two-person founding team

Pre-launch startup designed to let people send money abroad over WhatsApp through licensed money-transfer companies.

  • Led development of the WhatsApp chatbot (Next.js, TypeScript, WhatsApp Cloud API) that completes a money transfer inside one chat. The bot uses LLM tool calling to quote exchange rates, run Persona KYC identity checks, collect recipient details, and send the customer a payment link, so nobody has to leave WhatsApp or fill out a form.
  • Designed the payment backend so no payment is ever charged or paid out twice. Every payment step carries an idempotency key, and each payment event is written through a transactional outbox in PostgreSQL, so a retry or a crash cannot repeat a charge. Customer data is envelope-encrypted, and every action lands in a full audit trail.
  • Built a partner dashboard, a REST API, and signed webhooks so licensed partners can review transfers, check compliance, and connect their own systems. Deployed the platform on Vercel with Neon Postgres and Upstash Redis.
  • Next.js
  • TypeScript
  • WhatsApp Cloud API
  • LLM tool calling
  • PostgreSQL
  • Upstash Redis
  • Vercel
Aug 2025 – May 2026Fairfax, VA

George Mason University — Costello College of Business

AI Systems Engineer (Graduate Research Assistant)

Automated a professor’s trademark research, replacing manual data collection and image review with a scraper and a multimodal LLM.

  • Partnered with Dr. Saurabh Mishra to automate his trademark research. Built a Python scraper with caching and retry handling that collected ~200 USPTO opposition filings from TTABVue and TSDR and turned them into structured records ready for analysis.
  • Classified trademark images with Claude Vision (a multimodal LLM) at ~90% accuracy, which cut manual review time by ~60%.
  • Python
  • Web scraping
  • Claude Vision
  • Multimodal LLMs
Jan 2022 – May 2024India

KL University — Department of Computer Science & Engineering

Undergraduate Researcher, Applied ML

Ran applied machine-learning research that led to peer-reviewed publications.

  • Implemented 4 classifiers (Decision Tree, Random Forest, SVM, Logistic Regression), tuned each with grid search and cross-validation, and combined them into an ensemble for hair-fall prediction. The ensemble reached 93% accuracy, compared with 89% for the best single model.
  • Published 2 first-author papers, one on hair-fall prediction and one on AI in cybersecurity, and presented team research at IEEE ICICT 2023.
  • scikit-learn
  • Ensemble learning
  • Grid search
  • Cross-validation
Projects

Questions I answered

Each project starts with a question and ends with a measured answer. The charts are interactive.

01

Evaluation research · CS 692, advised by Prof. Bo Han

VLM Chart-Understanding Study

Can a frontier vision-language model still read a chart once the chart is drawn in 3D?

  • Evaluated GPT-5.4 on chart question answering with the ChartX benchmark: 6,000 chart images across 18 chart types. Accuracy fell from 85.7% on 2D charts to 59.3% on 3D charts, and McNemar’s test showed the drop is statistically significant.
  • Found why: 3D views hide or distort parts of the chart, so the model cannot read values it cannot see. Also found a flaw in the benchmark itself, where some questions asked for exact numbers the image never showed. Adding data labels to those charts raised accuracy from 51.6% to 97.7%.
  • GPT-5.4
  • ChartX benchmark
  • McNemar’s test
  • Python
GPT-5.4 accuracy on ChartX
2D charts85.7%
3D charts59.3%
▼ 26.4 points

Same benchmark, same model: moving the charts into 3D cost 26.4 points of accuracy, because 3D views hide or distort the values the questions ask about.

02

Fine-tuning · Personal project

Finance-Tuned Llama 3.2 1B

Can a small model learn finance without forgetting everything else it knew?

  • Fine-tuned Llama 3.2 1B Instruct on 5,675 finance examples with LoRA (Hugging Face PEFT, TRL SFTTrainer) and published the model on Hugging Face. Cleaned the training data first, removing 72% of 20,000 loaded examples as noisy or duplicate.
  • Benchmarked every version on MMLU, GSM8K, and IFEval. An earlier run lost 7.4 MMLU points to catastrophic forgetting, so I traced the cause and fixed it: lowered the LoRA rank to 8, trained only the attention layers, cut the learning rate 5x, and trained for a single epoch.
  • Held the final model at 45.9% on MMLU vs. 46.1% for the base model, and recovered 25.9 points on GSM8K and 15.7 points on IFEval compared with the earlier run. Training took under 7 minutes on one NVIDIA A100.
  • LoRA
  • Hugging Face PEFT
  • TRL SFTTrainer
  • MMLU · GSM8K · IFEval
Benchmark scores (%)
MMLUgeneral knowledge, 57 subjects
GSM8Kgrade-school math reasoning
IFEvalinstruction following

The earlier run collapsed on math (33.6% → 6.1% on GSM8K). The final model stayed within 2.1 points of the base model on all three benchmarks.

03

Self-hosted AI mail platform · TypeScript

Mail Agent

Can one private inbox triage and draft replies across every email account I own?

  • Created a self-hosted web app that combines 5 email accounts (Gmail, iCloud, Fastmail, Zoho) into one inbox, with LLM triage and reply drafting powered by Gemma via Ollama, running locally or in the cloud.
  • Encrypted stored credentials with AES-256-GCM and sandboxed email HTML in an iframe, so a malicious email cannot run code inside the app. Automated follow-ups stop on their own when the recipient replies or unsubscribes.
  • TypeScript
  • Gemma via Ollama
  • AES-256-GCM
  • LLM triage
AI Lab

Don’t just read it. Test it.

Three working AI tools, built into this site. Each one shows a skill from my resume: retrieval with citations, structured LLM output checked by code, and a model I fine-tuned.

Ask about my work

Ask anything about my experience, projects, research, or skills. The assistant answers only from this site’s content and cites the section each fact comes from.

How it works
  1. BM25 retrieval picks the most relevant passages from my resume.
  2. An open LLM answers using only those passages, citing each one.
  3. The server drops any citation that doesn’t match a real passage.
Research

Peer-reviewed publications

IJRITCC · 2023 · First author

Enhancing Hairfall Prediction: A Comparative Analysis of Individual Algorithms and an Ensemble Method

Read the paper ↗
IJISAE · 2023 · First author

Assessing the Effectiveness of Artificial Intelligence Techniques in Mitigating Cybersecurity Risks

5 peer-reviewed papers (2 first-author, 50+ citations), including IEEE ICICT 2023.

Full list on ORCID ↗
Skills

The toolkit

Languages & Backend

  • Python
  • TypeScript
  • SQL
  • Bash
  • Next.js
  • FastAPI
  • PostgreSQL
  • Redis

LLM & Agents

  • Claude API
  • OpenAI API
  • Ollama
  • Tool calling
  • RAG
  • Embeddings
  • Hybrid search
  • Chroma
  • Prompt engineering

ML & Training

  • PyTorch
  • Hugging Face Transformers
  • TRL
  • PEFT
  • LoRA
  • QLoRA
  • DPO
  • GRPO
  • scikit-learn

Deployment & Evaluation

  • Docker
  • CI/CD
  • Vercel
  • AWS
  • vLLM
  • GGUF
  • Quantization
  • LLM evaluation (MMLU, GSM8K, IFEval)
Education & certifications

Trained & certified

M.S., Computer Science

George Mason University · Fairfax, VA

GPA 3.57 / 4.00May 2026

B.Tech, Computer Science & Engineering

KL University · India

GPA 8.7 / 10May 2024
Contact

Let’s build something that works.

Email is the fastest way to reach me. My resume, LinkedIn, and this site tell the same story.