Sahil Suriya

AI/ML • 24 years • Bengaluru, India • UTC+05:30 • In office, Partially remote, Fully remote • Relocation • Work permits: India • Citizenship: India • English: C1 • Can start in 2 weeks • from $20k per year

AI Engineer

Python

SQL

Active 4 hours ago

Invite to interview

Download CVCV

Overview

Technical skills

Projects

Timeline

Roles

Overview

I am an AI/ML Engineer with over one year of hands-on experience building Generative AI applications, Retrieval-Augmented Generation (RAG) pipelines, agentic AI systems, and scalable Python backend services. At VectorStack, I have worked with Python, FastAPI, LangChain, LLMs, vector databases, MongoDB, and PostgreSQL to develop production-oriented AI solutions, including document question-answering systems and an F1 racing chatbot. I enjoy solving complex problems, learning emerging technologies, and transforming AI concepts into practical applications. With a Master of Computer Applications (MCA) degree, I am looking for opportunities to contribute to innovative AI products, strengthen my engineering expertise, and build reliable, scalable AI systems that deliver measurable business value.

Phone

Technical skills

Languages

Python

SQL

DevOps

Rest API

AWS

Azure

GitHub

Docker

Git

AI/ML

LLM

Gemini

LangChain

LoRA

Transformers

Scikit-learn

TensorFlow

PEFT

QLoRA

RAG

BERT

Hugging Face

OpenAI

RLHF

LangSmith

Other

FastAPI

Flask

Selenium

Chroma

FAISS

AI Agents

Machine Learning

Embeddings

Fine-tuning

Prompt Engineering

Function Calling

Semantic Search

NLP

ETL/ELT

Sentiment Analysis

Projects

News Summarization & Sentiment Analysis

Built a FastAPI service that aggregates news from multiple sources and generates transformer-based summaries. Added comparative sentiment scoring and automated daily digests for business stakeholders. The implementation aimed to reduce manual analysis workload through scheduled, structured outputs.

LLM-Powered Voice Assistant for Financial Transactions

Engineered a secure voice assistant that interprets natural-language commands for financial transactions. Integrated Gemini for LLM understanding alongside speech-to-text input. Focused on high command recognition across multiple transaction types for a functional demo presented at a hackathon.

Agentic RAG Document QA Chatbot (Multi-Format)

Developed an agent-based RAG document QA component that retrieves answers across multiple file types such as PDFs, DOCX, HTML, and CSVs. Used LangChain with a FAISS-based retrieval pipeline and an embeddings workflow to improve extraction accuracy. Designed it for enterprise-style reuse with evaluation-driven iteration to raise performance in an internal pilot.

Timeline

AI/ML Engineer • Middle

VectorStack • Full-Time

Sep 2025 to Present 1 Year 1 Month Bengaluru In office

Built a RAG chatbot for answering Formula 1 questions using race data, driver stats, and session transcripts. Implemented FastAPI services and MongoDB-backed ingestion pipelines (collect, chunk, embed, store). Improved retrieval relevance by aligning transcripts with race events and reduced API response times via query optimization and caching. Also delivered Python/FastAPI REST APIs for a shipping platform with admin-driven reassignment workflows.

RAG

Python

Rest API

Visvesvaraya Technological University (VTU)

Master's Degree • Computer Science and Artificial Intelligence

2023–2025 Belagavi, Karnataka

AI Data Curation and RLHF Intern • Junior

Skypoint • Internship

Mar 2024 to May 2024 2 Months Bengaluru In office

Automated RLHF dataset collection with Python-based automation. Built preprocessing and ingestion pipelines to produce high-quality datasets for model training. Reduced both collection and processing time through pipeline automation and optimizations.

Python

RLHF

BMS College of Engineering (BMSCE)

Bachelor's Degree • Computer Application

2020–2023 Bengaluru, Karnataka