Raghav Raman
book a call ↗

Bihar, India · Python · Data · AI

Raghav
Raman

Python backend engineer

Backend and data engineer with 4 years of experience building APIs, ETL pipelines and AI search systems with FastAPI, Python, MySQL, FAISS and RAG, deployed on Linux and Nginx.

Explore my work ↓Get in touchBook a call ↗
4+ years5 featured buildsAI + data focus
RR / 01ENGINEERING
Raghav Raman OPEN TO BUILD
RAGHAV RAMANPYTHON · DATA · AI
04+YEARS
BUILDING
APIETL
RAG
HOW I BUILDDATA → INTELLIGENCE
01SQLDATA
02ETLTRANSFORM
03APISERVE
04RAGREASON
structuredprocessedconnectedsemantic
PYTHON✦FASTAPI✦PYTHON✦SQLALCHEMY✦MYSQL✦FAISS✦OPENAI✦RAG✦ETL✦CELERY✦REDIS✦DOCKER✦NGINX✦ PYTHON✦FASTAPI✦PYTHON✦SQLALCHEMY✦MYSQL✦FAISS✦OPENAI✦RAG✦ETL✦CELERY✦REDIS✦DOCKER✦NGINX✦

01 · Morning

About me

I'm a Python developer and data engineer with 4 years of experience designing, building and deploying scalable backend, web, desktop and automation systems. I'm strongest in FastAPI, Python, REST APIs, SQL performance work and ETL, and recently I've gone deep on AI data platforms: semantic search, embeddings and vector retrieval.

Away from the keyboard I'm drawn to philosophy, poetry and creative exploration, which keeps the engineering thoughtful.

Based
Bihar, India
Experience
4 years
Focus
Backend · ETL · AI search
Education
B.Tech, Electronics & Comm. (2022)
Now
Analyst, Capgemini
Studying
Cybersecurity (2026–27)

02.25 · Noon

What I like building

The common thread across my work: turning messy inputs into useful, searchable, dependable systems.

01

Data → decisions

ETL pipelines, validation, transformation and SQL systems that make operational data easier to trust and use.

source→transform→serve
02

Documents → answers

RAG and semantic retrieval systems that turn unstructured knowledge into grounded application experiences.

docs→vectors→answer
03

Events → automation

Background jobs, queues, browser automation and desktop tooling that remove repetitive work from a workflow.

event→worker→result
04

Systems that stay observable

I care about the layer after “it works”: indexes, caching, pagination, structured APIs, logging, deployment and maintainability.

APIDBQUEUECACHEVECTORLINUX

02.5 · Early afternoon

Experience & trajectory

2022 — presentCapgemini

Analyst · Data & Engineering

Working across data engineering and BI-oriented delivery, with hands-on practice in ETL workflows, SQL, Informatica ecosystems and cloud data concepts.

ETLSQLInformaticaBI
2024 — 2026Independent builds

Backend → AI systems

Built increasingly capable systems around FastAPI, Python, vector retrieval, RAG, automation, data pipelines and self-hosted infrastructure.

FastAPIRAGFAISSDocker
2026 — nextLearning in public

Broadening the engineering stack

Deepening cloud, cybersecurity, distributed systems and AI-agent concepts while turning experiments into reusable tools and polished products.

CloudSecurityAgentsSystems

03 · Late morning

Technical skills

A practical stack spanning backend engineering, data engineering, AI retrieval and production infrastructure.

Backend & APIs

PythonFastAPIPythonREST APIsSQLAlchemyPydanticCeleryRedis

Data & ETL

SQLOracleMySQLDB2SnowflakeInformatica IICSIDMCPowerCenterSCD Type 1/2Data validation

AI & Retrieval

RAGFAISSEmbeddingsOpenAI APIsLangChainVector searchSemantic searchAI agents

Automation & Computer Use

PlaywrightOpenCVFFmpegPyQt6PynputBrowser automationDataset generation

Cloud & Platforms

AWSGoogle CloudBigQueryDatabricksMongoDBKafkaConfluentDocker

Production & Engineering

LinuxNginxGitPytestPerformance tuningAPI designETL architectureData quality

04 · Midday

Five systems. One engineering mindset.

Each project gets the same level of detail — what it does, how it is built, and the engineering decisions behind it.

Currently highlightingAI data platforms · backend APIs · retrieval systems · offline utilities
01

AADI: Intelligent Data Recording Agent

Python · PyQt6 · OpenCV · FFmpeg · Playwright · Pynput

Desktop capture and event-recording system for producing structured Computer Use Agent training data.

Desktop agentComputer useEvent captureDataset generation

What I built

  • Screen, keyboard, mouse and scrolling capture with structured event logs.
  • Activity grouping and browser interaction capture using Playwright.
  • Video processing and dataset preparation workflows with FFmpeg/OpenCV.

Engineering focus

PyQt6OpenCVFFmpegPlaywrightPynput
Signal: several production iterations used internally for dataset preparation and quality improvement.
02

RAG Document Q&A API

FastAPI · LangChain · FAISS · Redis · Celery

Retrieval-augmented API that turns uploaded documents into searchable, grounded answers.

RAGVector searchAsync jobsAPI

What I built

  • Document ingestion, chunking, embedding and vector-indexing pipeline.
  • Queue-based background processing for heavier ingestion tasks.
  • Retrieval endpoint returning grounded LLM answers as structured JSON.

Engineering focus

FastAPILangChainFAISSRedisCelery
Signal: separates ingestion, retrieval and API concerns so the system can evolve independently.
03

AI Code Testing & Bug Investigation Agent

Python · FastAPI · OpenAI Responses API · Function Calling · Pytest · Pydantic · Docker

AI-assisted testing agent that reads approved source/specification files, generates targeted Pytest cases and investigates behavior through controlled test execution.

AI testing agentBug investigationTool callingSandboxed execution

What I built

  • Agent workflow that reads approved source and specification files and generates targeted Pytest cases.
  • OpenAI Responses API tool-calling loop with read_file, write_test and run_tests tools.
  • Bounded investigation with append-only generated tests and structured JSON/Markdown reports separating test evidence from model analysis.

Engineering focus

OpenAI Responses APIFunction CallingPytestPydanticDockerFastAPI
Signal: generated tests run inside controlled Docker execution with resource/time limits, restricted filesystem access and external network access disabled.
04

ETL Validation Toolkit

Python · Pydantic · Pytest · MySQL

Reusable validation layer for cleaning, checking and preparing incoming data before database loading.

ETLData qualitySchema validationTesting

What I built

  • Validation pipeline for CSV, Excel and API feeds.
  • Schema checks and typed models using Pydantic.
  • Rejected-row reporting and automated tests before production loads.

Engineering focus

PythonPydanticPytestMySQL
Signal: shifts data-quality failures earlier in the pipeline instead of discovering them after loading.
05

Omni Suite: Offline File & Document Utility Platform

HTML · CSS · JavaScript · Browser APIs · Client-side Processing

A local-first utility website that brings PDF, image and file workflows into one browser-based suite without sending files to a server.

Live project ↗
Offline-firstPDF toolsFile conversionOCRCompression

What I built

  • All-in-one browser utilities for PDF and file workflows including merge, split, conversion, preview and local processing.
  • OCR and document extraction workflows, with support for image-based documents and practical browser-side processing.
  • File compression and decompression workflows plus image/file conversion utilities designed to run locally for privacy and repeatable offline use.
  • Tool-by-tool controls with previews before export, so users can inspect results instead of immediately downloading them.

Engineering focus

Vanilla JavaScriptBrowser APIsPDF processingOCRCompressionOffline workflows
Signal: designed as a self-contained utility suite with client-side processing, broad format handling, previews and modular studio-style tools that remain usable without a backend dependency.

05 · Afternoon

Certifications

Grouped for quick scanning — open a category or search the list.

⌕

Oracle Cloud Infrastructure 2024 Generative AI Certified Professional

Issued by Oracle. Certification in Oracle Cloud generative AI solutions.

AWS Cloud Quest: Cloud Practitioner

Issued by Amazon Web Services (AWS). Gamified cloud practitioner training with hands-on labs.

AWS Fundamentals Specialization

Issued by Amazon Web Services. Core AWS services, architectures, and fundamentals.

Google Cloud Computing Foundations Certificate

Issued by Google Cloud. Basics of compute, storage, and networking on GCP.

Data Warehousing Workshop by Snowflake

Issued by Snowflake. Modern data warehousing best practices and patterns.

Cloud Hero: Enhance Data Warehouses with BigQuery

Issued by Google. BigQuery optimization and advanced analytics techniques.

Generative AI Fundamentals by Databricks

Issued by Databricks. Large Language Models and vector workflows on Databricks Lakehouse.

NASA Open Science 101

Issued by NASA. Open science principles and reproducibility.

SI Associate Certification

Issued by MongoDB. Associate-level MongoDB credential covering MongoDB fundamentals.

AWS Partner: Generative AI Essentials (Business)

Issued by Amazon Web Services (AWS). Generative AI fundamentals for business contexts.

Introduction to Cybersecurity

Issued by Cisco. Foundational cybersecurity concepts.

Generative AI Fundamentals

Issued by Google. Foundational generative AI concepts and applications.

Databricks Lakehouse Fundamentals

Issued by Databricks. Lakehouse fundamentals; screenshot shows issued May 2024 and expired May 2025.

Google AI Essentials

Issued by Google. Practical generative AI and AI productivity fundamentals.

Introduction to Cyber Security

Issued by The Open University. Foundational cybersecurity concepts.

Cloud Hero: Core Infrastructure II

Issued by Google. Google Cloud infrastructure hands-on credential.

Cloud Hero: Vertex AI

Issued by Google Cloud Skills Boost. Vertex AI and prompt engineering fundamentals.

Cloud Hero: Getting started with Cloud Dev in GCP

Issued by Google. Getting started with cloud development on Google Cloud.

Meta Data Analyst Professional Certificate

Issued by Meta via Coursera. Analytics lifecycle and visualization.

Google Data Analytics Professional Certificate

Issued by Coursera (Google). Data cleaning, visualization, foundational analytics with SQL, Tableau, R.

Google Advanced Data Analytics Professional Certificate

Issued by Coursera (Google). Advanced data analysis, machine learning, regression, statistical modeling.

IBM Data Visualization Specialization

IBM credential covering data visualization, dashboards and communicating analytical findings.

Introduction to MongoDB by MongoDB

Issued by MongoDB University. NoSQL data modeling and CRUD operations.

Get Started with Tableau

Issued by Tableau/Coursera. Interactive dashboards and storytelling.

MongoDB SI Associate Certification

Issued by MongoDB. Operational skills and performance tuning.

IDMC Foundation Series Certification

Issued by Informatica. Basics of Informatica Data Management Cloud and data governance.

Informatica Cloud / IICS Certification

Informatica University credential covering cloud data integration and ETL workflows.

I&D Data Engineer IPC Grade A — Level 1

Data engineering industry certification covering foundational engineering practices.

Databricks Lakehouse Platform Accreditation

Databricks learning credential covering Lakehouse concepts, Delta workflows and platform fundamentals.

Claire GPT by Informatica

Issued by Informatica. AI-assisted data management capabilities.

Database Structures and Management with MySQL

Issued by Meta. MySQL database structures and management.

Marketplace & Cost Estimation Workshop

Issued by Snowflake. Snowflake marketplace and cost estimation.

Agile Software Development

Issued by University of Minnesota. Agile software development principles and practices.

SQL v/s NoSQL

Issued by Scaler. Comparative SQL and NoSQL database concepts.

Full Stack Generative and Agentic AI with Python

Issued by Udemy (2026). Python, OpenAI/Gemini APIs, RAG with LangChain, vector databases, LangGraph and MCP concepts.

Python for Data Science by IBM

Issued by IBM. Python programming for data analysis and science.

Version Control by Meta

Issued by Meta. Git workflows and collaboration fundamentals.

Fundamentals of Agile Project Management by PMI

Issued by Project Management Institute (PMI). Scrum, iterative delivery, agile concepts.

Quantum Computing for Everyone: Fractal

Issued by Fractal. Introduction to qubits and quantum algorithms.

Confluent Fundamentals: Apache Kafka

Issued by Confluent. Event streaming with Apache Kafka.

GCP Generative AI Fundamentals

Google Cloud credential covering foundational generative AI concepts and Google Cloud AI capabilities.

Game Theory

Certificate from IIM Ahmedabad covering strategic interaction, incentives and decision-making concepts.

Micro Certification: Welcome to ServiceNow

Issued by ServiceNow. Platform essentials and navigation.

Intro to Apache Cassandra™

Issued by Canvas Credentials (Badgr). Apache Cassandra fundamentals.

Talend Data Integration

Issued by Talend. Data integration and ETL fundamentals.

Agile Project Management

Issued by HP LIFE. Agile project management fundamentals.

Intel® Solution Pro - Principles of AI Everywhere

Issued by Intel. Foundational AI concepts and AI-everywhere principles.

Hadoop Foundations

Issued by IBM. Hadoop ecosystem and big-data fundamentals.

Data Integration and ETL with Talend

Issued by Edureka. Talend-based data integration and ETL concepts.

AI Skills Challenge

Issued by Microsoft. AI skills challenge credential.

Introduction to Mathematical Thinking

Issued by Stanford University. Mathematical reasoning and proof-oriented thinking.

GenAI in Data Analytics

Issued by Meta. Generative AI applications in data analytics.

Deploying and Evaluating GenAI Apps with MongoDB

Issued by MongoDB. Building and evaluating generative AI applications with MongoDB.

Academy Accreditation - Generative AI Fundamentals

Issued by Databricks. Generative AI fundamentals accreditation; screenshot shows issued Oct 2024 and expires Oct 2026.

Know Thyself

Issued by University of Edinburgh. Self-knowledge and reflection.

Mindfulness

Issued by KAIST. Attention, presence, and mindfulness practice.

Communicating with Presence

Issued by IESE Business School. Executive communication skills.

EF SET English Certificate

Standardized English proficiency certification.

Learn with Workday by Workday

Career and skills development.