Hi, I'm Vigneshkumar Selvaraj.
A
Self-driven, quick starter, passionate programmer with a curious mind who enjoys solving a complex and challenging real-world problems.
About
AI & Cloud Software Engineer with experience building LLM applications, AI agents, RAG systems, and enterprise AI solutions across Audi AG, Fraunhofer IKS, and Bosch.
Developed and deployed production-ready AI systems using Python, FastAPI, AWS, Docker, LangChain, vector databases, and modern LLM frameworks.
Experience spanning multi-agent systems, conversational AI, knowledge retrieval, document intelligence, and AI-powered automation for industrial and enterprise use cases.
Strong interest in Agentic AI, AI evaluation, reasoning systems, knowledge graphs, and scalable AI architectures.
Experience
- Built and optimized LLM and RAG-based systems for automating document analysis and requirement extraction.
- Designed evaluation and validation workflows integrating data ingestion, preprocessing, and quality assessment for production AI systems.
- Deployed AI models using Docker and AWS CDK, optimizing latency for cloud and edge environments.
- Collaborated with cross-functional teams to integrate AI capabilities into enterprise workflows, improving automation and information accessibility.
- Developed an end-to-end LLM assistant for industrial production environments using FastAPI and LangChain.
- Built scalable RAG pipelines with FAISS embeddings for knowledge retrieval from technical documents.
- Implemented semantic retrieval and context-aware response generation to improve AI-assisted decision support.
- Deployed system on AWS (ECR, ECS) ensuring high availability and CI/CD workflows.
- Collaborated with researchers and engineers to productionize AI prototypes into real systems.
- Built scalable backend systems using FastAPI and Docker in production environments.
- Developed OCR + ML pipeline for automated data extraction and classification.
- Optimized pipelines using multiprocessing, improving performance and efficiency.
- Worked with structured and unstructured data using SQL and MongoDB.
Projects
A music streaming web app based on Django
- Tools: Django, HTML, CSS, Bootstrap, SQLite, AWS S3, Heroku
- Register/login to the web app(with OAuth-based Google Sign-In).
- Search and filter songs based on language and singer.
- Create multiple playlists and add/remove songs to/from playlist.
- Scroll through recently played/viewed songs.
An attention-based classification model that aims at generating an answer for a given input image.
A Seq2Seq model that generates a short summary of the given input video.
An image generator based on the concept of adversarial networks (GANs)
Skills
Languages and Databases
Python
HTML5
CSS3
MySQL
PostgreSQL
Shell Scripting
Libraries
NumPy
Pandas
OpenCV
scikit-learn
matplotlib
Frameworks
Django
Flask
Bootstrap
Keras
TensorFlow
PyTorch
Other
Git
AWS
Heroku
GenAI & AI Systems
LangChain
Development
Python
FastAPI
Pydantic
Cloud & Deployment
AWS
Docker
Databases
MySQL
PostgreSQL
MongoDB
GenAI & AI Systems
LangChain
LangGraph
LangSmith
MCP
Development
Python
FastAPI
Pydantic
Cloud & Deployment
AWS
Docker
CI/CD
Databases
MySQL
PostgreSQL
MongoDB
Education
Germany
Degree: M.Sc. International Information Systems
Duration: 10/2024 - 03/2027
Major: AI and Software Development
Grade: 2.0/4.0
Classification: Good
Chennai, India
Degree: Bachelor’s in Computer Science
Duration: 07/2017 - 04/2021
Major: Data Science and Software Development
Grade: 8.81/10
Classification: First Class with Distinction
Bachelor Thesis: Image caption generator using CNN and RNN