SYSTEM STATUS: ONLINE // BANGALORE (IST)
[ENV: FASTAPI · OLLAMA · CUDA · DOCKER · RAGAS]
OPEN TO AI/ML INTERNSHIPS · BANGALORE / HYDERABAD / DELHI / REMOTE

AI systems engineered for <production_scale>

FOCUS: AI/ML Systems Engineer

I'm Chetan — an AI/ML Engineer building production LLM and RAG systems for fintech and risk intelligence platforms. I fine-tune transformer models with LoRA, wire automated RAGAS evals & guardrails into pipelines, and deploy async FastAPI microservices that hold response latencies sub-second and uptime at 99%+.

./view_projects.sh get_in_touch()
RUNNING
def execute_risk_query(query: str):
# Step 1: Dense + Sparse Hybrid Search
context = retriever.hybrid_search(query, top_k=12)
# Step 2: LoRA Llama 3.1 Inference
response = model.generate(context, guardrail=True)
# Step 3: RAGAS Faithfulness Verification
score = ragas.verify_faithfulness(response)
return response, score
● FastApi Worker [CUDA:0]
>_ LIVE SYSTEM DIAGNOSTICS p95: 38ms
skills projects eval bio contact clear
Type a command or click a chip above (e.g. 'skills', 'eval', 'projects').
chetan@sys:~$
VRAM AllocationCUDA 12.4
6.2 / 8.0 GB
Generation SpeedLoRA 8B
78 tok/s
RAGAS FaithfulnessMin: 0.85
0.94
p95 API LatencySub-second
38ms
UPTIME: 99.7% CONTAINER: ACTIVE [risk-minor-api:v2.1]
2
// PRODUCTION INTERNSHIPS
10+
// SHIPPED & OSS PROJECTS
99%+
// SERVICE UPTIME MAINTAINED
200+
// LEETCODE PROBLEMS SOLVED
FEATURED_SYSTEMS

Production Architectures & Evals

Not prompt wrappers — real evaluation harnesses, adapter pipelines, and consensus systems shipped in fintech and risk domains.

Risk Minor

PRODUCTION

Multi-agent risk intelligence platform for regulatory filings. Combines BM25 keyword search with Milvus dense vector retrieval, a fine-tuned Llama 3.1 8B inference layer, input/output validation guardrails, hallucination-detection fallbacks, and real-time RAGAS + Langfuse quality tracing across all pipeline nodes.

FastAPIMilvusRAGASLangfuseLlama 3.1
Inspect Architecture →

Multilingual LoRA Fine-Tuning

PRODUCTION

Fine-tuned Llama 3.1 8B using LoRA with adapter merging across 8 Indian languages — Assamese, Bengali, Gujarati, Kannada, Marathi, Nepali, Tamil, Malayalam — enabling automated legal document translation and multilingual regulatory compliance support with preserved language fidelity.

LoRALlama 3.1PEFTPyTorchHuggingFace
View Internship Work →

Fact Check Multi-Agent

OPEN-SOURCE

Fake-news detection engine running 3 local LLMs — Qwen 2, Phi-3, LLaMA 3.1 — in parallel via Ollama, aggregating verdicts through a weighted consensus layer with optional DuckDuckGo live web context injection to eliminate single-model hallucination and recency bias.

OllamaStreamlitMulti-AgentRAGAS
View Source Code →
INTERACTIVE_TESTBENCH

Live RAG Architecture Simulator

Experience how queries travel through Chetan's production pipeline — from dense/sparse retrieval and LoRA inference to RAGAS hallucination guardrails.

PRESET_QUERIES: Click a scenario or type a custom query below:
// STAGE 01
Tokenization & Embedding
FastAPI tokenizer generates 1536-dim vectors.
// STAGE 02
Hybrid Retrieval
BM25 + Milvus dense vector search (top_k=12).
// STAGE 03
LoRA Llama 3.1 8B
Quantized CUDA inference with merged adapters.
// STAGE 04
RAGAS Guardrails
Faithfulness eval & zero-hallucination check.
>_ SYSTEM RESPONSE STREAM:
[READY] Click "EXECUTE PIPELINE ⚡" or pick a preset query to run the simulated architecture.
LATENCY: 38ms (p95) FAITHFULNESS: 0.94 GUARDRAIL: PASSED VRAM: 6.2 GB
SYSTEM_READY

Looking for an AI engineer who ships & measures?

Available for internships & full-time roles in AI/ML Engineering, RAG Development, and LLM Infrastructure.

› ESC to close
Navigation
🏠 01. Home Overview
Page
💼 02. Experience & Internships
Page
🚀 03. Projects (12 Systems)
Page
👤 04. About & Tech Stack
Page
✉️ 05. Contact & IDE Shell
Page
Featured Systems
⚡ Risk Minor (Milvus + LoRA Llama 3.1)
RAG
🗺️ AstraRoute Navigation Engine (OSRM + Scrapling)
Infra
👁️ AI Blur & Quality Detector (OpenCV API)
Vision
✈️ Airbus FCOM Precision QA Engine
RAG
Quick Actions
◐ Toggle Theme (Dark / Light)
Action
📋 Copy Email (chhetrichetan45@gmail.com)
Clipboard
🔊 Toggle Audio FX Sounds
Setting