Rohan Biswas
● Open to Work

Rohan Biswas

Fresher, SDE, ML/AI Engineering
India

About Me

Backend-focused Software Engineer (B.Tech CSE, 2025) and IISc FAST-SF Research Fellow with hands-on experience designing and deploying production backend systems in Python. Built and shipped RESTful APIs and containerized microservices (FastAPI, Docker), including a multi-agent LLM/RAG backend live on Hugging Face Spaces and a full-stack data pipeline (PostgreSQL, FastAPI) serving live predictions through a deployed dashboard. Comfortable across the stack: relational database design, REST API development, object-oriented backend architecture, and containerized deployment, with applied depth in LLM integration, embeddings, semantic search, and AI agent orchestration.

Skills & Technologies

PythonSQLJavaScriptC/C++PyTorchTensorFlowScikit-learnHuggingFace TransformersLangChainRAGNLPAgentic SystemsLSTMNMFPCAGenAIPandasNumPyPostgreSQLMySQLChromaDBTime-Series AnalysisStatisticsFastAPIDockerGitStreamlitFlaskReactJSLinuxPowerBIMS ExcelMS PowerpointTypescriptREST APIsMicroservicesExpressJSNode.jsOOPData Structures & AlgorithmsAWSRelational DatabasesData WorkflowsHugging Face TransformersAI AgentsVector DatabasesEmbeddingsSemantic SearchPrompt EngineeringTime-Series ForecastingLlamaindexAgile MethodologiesOpen-Source Contributions

Work Experience

Research Intern: Simulation & ML Infrastructure

Indian Institute of Science (IISc), Dept. of ECE
Jun 2024Aug 2024

Received the FAST-SF Fellowship from IISc’s Dept. of ECE. Built a modular Python simulation framework for multi-agent orchestration and automated test pipelines. Ran over 40 experiments to identify failure modes and documented root causes, improving simulation fidelity.

Projects

Adaptive PCA Portfolio Analytics

Built a rolling PCA factor decomposition pipeline across 9 global equity indices using adaptive 60-day windows to detect regime shifts and non-stationarity in live data.

Python

EpiRAG - Containerized Microservice, Multi-Agent Backend

Architected a multi-agent retrieval-augmented generation (RAG) system for scientific literature, combining autonomous debate, confidence estimation, retrieval optimization, and citation verification across multiple LLMs.

PythonFastAPIDocker

Nifty50 Stock Forecasting System - Full Stack

Engineered a full-stack system in Python: designed a PostgreSQL relational schema for data ingestion, built a RESTful FastAPI service layer, and shipped a live Streamlit dashboard serving model predictions end-to-end.

PythonPostgreSQLFastAPIStreamlit+1

Education

B.Tech

Computer Science and Engineering

Tezpur University2021 - 2025
Rohan Biswas - Fresher, SDE, ML/AI Engineering | HiringAnt