available for opportunities

Sahil Sohani

Backend Engineer

I build backend systems, AI pipelines, and distributed infrastructure. Published IEEE researcher. AdvaRisk · DRDO.

FastAPIPythonDistributed SystemsLLMs & RAGNLPComputer Vision
GitHub$ contact

4

Projects Built

2

IEEE Publications

2

Industry Internships

sahil@portfolio:~
$cat skills.txt
FastAPI · Celery · RabbitMQ · Redis · MongoDB
DistilBERT · FAISS · YOLOv8 · Groq · LangChain
Docker · OracleDB · ClickHouse · SQLAlchemy
$cat status.txt
Available for opportunities · B.E. CSE 2026 · CGPA 9.16
$

Education

B.E. Computer Engineering

Dr. D.Y. Patil Institute of Technology, Pune

CGPA 9.16 / 10.00·2022 – 2026

/projects

Featured Systems

Production software built to handle real workloads. Each project reflects deliberate engineering decisions.

AI Pipeline

InvoSure

Personal Project

AI-powered invoice verification system

Built an AI-powered invoice verification system using Groq LLM for vendor and GST entity extraction, automated GST verification via Playwright and 2Captcha, with a Dockerized FastAPI backend and React frontend.

PythonFastAPIGroq LLMOCRPlaywrightRedisMongoDBReact
AI Agent / RAG

PI-EVA — MA-RAG

Research

Uncertainty-aware multi-agent RAG pipeline

Production-style Multi-Agent RAG pipeline on HotpotQA using FAISS vector retrieval, Groq LLM orchestration, and Paraphrase-Induced Epistemic Variance (PI-EVA) for uncertainty quantification. EM: 44.0 | F1: 54.29.

PythonFAISSSentence-TransformersGroqHotpotQA
Computer Vision

ResQ Vision

Personal Project

Real-time CCTV accident detection system

Real-time CCTV accident detection using YOLOv8. FastAPI backend, Streamlit dashboard, accident evidence clip generation, SOS alerts via Telegram, and GPT-4o Mini for contextual descriptions. Deployed on LeapSwitch via Cloudflare Tunnel.

YOLOv8FastAPIReactOpenCVDockerCloudflare Tunnel
NLP

Feedback Sentiment Analyzer

Deployed

Offline NLP feedback classification for DRDO ERP

Fully offline real-time sentiment analysis system using DistilBERT. Classifies feedback into complaints, queries, suggestions, and appreciation. Integrated into DRDO internal ERP portal, reducing manual processing by over 70%.

PythonDistilBERTFastAPIStreamlitOracleDBDocker

/experience

Engineering Experience

Production internships building systems that handle real data, real scale, real pressure.

March 2025 – June 2025

Backend Development Intern

AdvaRisk, Baner, Pune

Mission

Built and maintained RESTful APIs, async task pipelines, and scraper orchestration systems for a financial risk intelligence platform.

Engineering Impact

  • Developed and maintained RESTful APIs using FastAPI and SQLAlchemy for scalable web scraping and data ingestion pipelines.
  • Automated VMN services and scraper orchestration, improving data reliability while reducing manual intervention.
  • Implemented asynchronous task queues using Celery, RabbitMQ, and Redis to improve scraping throughput and backend performance.
  • Worked on cloud deployment and virtual machines using LeapSwitch.
  • Provided production support in an Agile environment using Jira.
FastAPICeleryRabbitMQRedisMongoDBMySQLClickHouseSQLiteSQLAlchemyWeb ScrapingJira

September 2024 – December 2024

Research & Development Intern

DRDO – Defence Research & Development Organisation, Dighi, Pune

Mission

Developed a fully offline real-time feedback sentiment analysis system integrated into DRDO's internal ERP portal.

Engineering Impact

  • Built a fully offline real-time feedback sentiment analysis system using DistilBERT.
  • Classified textual feedback into complaints, queries, suggestions, and appreciation.
  • Integrated the solution into DRDO's internal ERP portal.
  • Eliminated manual category selection and star ratings, reducing processing time by over 70%.
  • Developed a scalable FastAPI backend with OracleDB and a Streamlit frontend.
PythonDistilBERTNLPFastAPIStreamlitOracleDBDocker

/research

Publications

Peer-reviewed research at the intersection of AI systems and real-world deployment. Two IEEE publications in 2026.

IEEE2026IEEE International Conference on Intelligent and Sustainable Electronics & Computing Technologies

Uncertainty Aware Multi-Agent RAG Using Paraphrase-Induced Epistemic Variance Analysis

Designed an uncertainty-aware Multi-Agent RAG framework that quantifies epistemic uncertainty using paraphrase variance. Improves response reliability through confidence-aware reasoning on multi-hop QA benchmarks.

Key Contribution

Introduced Paraphrase-Induced Epistemic Variance (PI-EVA) as a method to detect hallucination risk in RAG outputs. Achieved Exact Match of 44.0 and F1 of 54.29 on HotpotQA dev-distractor.

RAGMulti-AgentUncertainty QuantificationLLMNLP
IEEE2026International Conference on Contemporary Engineering & Technology (ICCET) · IEEE I2ITCON 2026

InvoSure: Smart GST Invoice Verification System

Proposed an AI-driven invoice validation framework combining OCR, LLM-based entity extraction, and automated GST verification. Designed a scalable backend architecture for end-to-end invoice processing.

Key Contribution

Combined OCR text extraction, Groq LLM entity parsing, and Playwright-based automated GST portal verification into a single pipeline — eliminating manual invoice validation entirely.

OCRLLMGST VerificationFastAPIAutomation
More publications on Google Scholar and IEEE Xplore.

/philosophy

How I Build Software

Principles that guide every architectural decision, not aspirational values posted on a wall.

01

Build for observability.

Logs, metrics, and traces from day one. If you cannot measure it, you cannot debug it in production.

02

Automate the repetitive.

Every manual step is a future outage. Infrastructure-as-code, CI/CD, and self-healing systems reduce human error.

03

Measure before optimizing.

Profile first. Premature optimization creates complexity without evidence of bottlenecks.

04

Prefer simple architectures.

A well-designed monolith often outperforms a poorly-designed microservice mesh. Complexity must be justified.

05

Fail gracefully.

Dead-letter queues, retries with backoff, circuit breakers. Systems fail — design so they degrade, not collapse.

06

Design systems that scale.

Stateless services, horizontal partitioning, async task distribution. Build for 10x before you need it.

/contact

Get in Touch

sahil@portfolio:~
$whoami
sahil sohani — backend engineer & researcher
$cat about.txt
B.E. Computer Engineering, Dr. D.Y. Patil Institute of Technology, Pune
CGPA: 9.16 / 10.00 · Batch of 2026
Interned at AdvaRisk (Backend) and DRDO (R&D)
2x IEEE Publications · Oracle Certified AI Professional
$cat contact.json
$