Open to Werkstudent, internship & full-time AI/ML roles in Germany

Hi, my name is

Gagandeep Shivanna

I build

I spent two years shipping enterprise backends and now work on GenAI full time: RAG pipelines, eval harnesses, and Infrastructure-as-Code. Based in Berlin, Germany, work permitted.

View WorkResume
  • M.Sc. Big Data & AI @ SRH Berlin
  • 2+ yrs enterprise backend
  • Conference publication
  • Production LLM apps
Prototype fast. Ship to production. Measure everything.
The rule behind every project below

Featured Projects

Built to ship, not just to demo. Each one solves a real problem end to end.

DataGrid: AI-Powered Analytics Platform

Live Demo

Challenge

Non-technical users can't query data without SQL.

Solution

Production-deployed analytics platform with a natural-language-to-SQL pipeline, sandboxed query execution, real-time SSE streaming, and auto-generated Recharts visualizations. Includes a Gaussian Copula synthetic-data engine with fidelity metrics and a text-to-SQL eval harness with execution-accuracy benchmarking tracked in MLflow.

Key decisions

Two-model Claude Sonnet/Haiku split for cost/latency; DuckDB for in-process analytical queries; execution-accuracy eval harness over exact-match.

  • FastAPI
  • React
  • DuckDB
  • Claude Sonnet/Haiku API
  • MLflow
  • SDV
  • Recharts
  • Vercel
  • Render

AsyncMeet (MANAN): AI Async Decision-Making Platform

Active Development

Challenge

Live meetings are expensive and exclude async/distributed teams.

Solution

A SaaS platform that replaces live meetings. Teams submit input asynchronously through a guided chat powered by Claude Sonnet, which asks follow-up questions on its own, then synthesizes all responses into a structured decision summary on a real-time WebSocket dashboard.

Key decisions

WebSocket dashboard for live state; Claude-driven adaptive follow-up questioning.

  • FastAPI
  • React/TypeScript
  • Claude Sonnet API
  • WebSockets
  • Python

AWS Account Onboarding Automation

Challenge

Manual AWS account setup is slow, inconsistent, and error-prone.

Solution

An Infrastructure-as-Code pipeline that provisions complete AWS accounts from a single YAML config: IAM users, groups and policies, S3 buckets, and VPC networking, all through Terraform and GitHub Actions with OIDC auth. It also writes a per-user runbook after every deploy.

Key decisions

OIDC over long-lived keys; single-YAML config as the source of truth.

  • Terraform
  • GitHub Actions (OIDC)
  • AWS
  • Python

Master's Thesis: A Failure Taxonomy of LLM-Generated Infrastructure-as-Code

In Progress

Challenge

LLMs generate Terraform that fails in ways nobody has systematically mapped.

Solution

Research into LLM self-repair of Terraform across syntax, security, and policy verification stages, with a PRISMA-style literature-review pipeline built on arXiv/OpenAlex APIs.

  • Python
  • arXiv/OpenAlex APIs
  • Terraform
  • LLM evaluation

Behind the Code

From enterprise Java in Bangalore to LLM research in Berlin.

0+
Years professional experience
0
Featured projects
0
Conference publication
0
Cloud platforms (AWS, Azure, GCP)

My path didn't start with AI. It started with two years of enterprise Java/Spring Boot at Vrize in Bangalore. Real production systems for real clients, where a bad deploy meant angry users, not a failed notebook cell. That's where I learned to care about testing, CI/CD, and code that other people can maintain.

Then LLMs changed what software could do, and I wanted in, not as a spectator. So I moved to Berlin for an M.Sc. in Big Data & AI at SRH (graduating Sept 2026), where I now also work as a Research Assistant building NLP pipelines under Prof. Dr. Alexander Iliev.

The result is a rare combination: I build AI products with backend-engineer discipline: sandboxed execution, eval harnesses, streaming APIs, and Terraform-managed infrastructure. Prototypes are easy. Things that stay up are not.

  • M.Sc. Big Data & AI, SRH BerlinGraduating Sept 2026
  • Research Assistant, NLP pipelinesRAG, prompt engineering, document classification
  • Berlin, GermanyStudent visa, work permitted
  • English (C2) · German (B1) · Kannada (Native)

Experience

From enterprise sprints in Bangalore to research in Berlin.

  1. 09/2025 – 04/2026 · Berlin, Germany

    Research Assistant @ SRH University of Berlin

    • Built and evaluated NLP pipelines for document classification and information extraction, applying prompt engineering and RAG under Prof. Dr. Alexander Iliev.
    • Synthesized research across cognitive science and AI ethics into structured academic writing.

  2. 09/2022 – 07/2024 · Bangalore, India

    Associate Software Engineer @ Vrize India Pvt Ltd

    • Developed enterprise Java/Spring Boot applications (Zaxby's, Tonic): scalable RESTful APIs and microservices across MySQL & MongoDB.
    • Architected modular backend services with Dependency Injection and AOP patterns to reduce coupling across service layers.
    • Led API debugging and unit/integration testing with JUnit and Mockito, enforcing code quality through structured peer reviews.
    • Automated deployment pipelines with Docker + Jenkins CI/CD, reducing manual release overhead across environments.
    • Delivered in Agile sprint cycles, recognized for technical ownership and cross-functional collaboration.

Education

07/2024 – Expected 09/2026 · Berlin, Germany

M.Sc. Big Data & Artificial Intelligence (120 ECTS)

SRH University of Berlin

Cloud across AWS, Azure & GCP; ML, deep learning, data engineering, distributed systems.

2018 – 2022 · Bangalore, India

B.E. Information Science & Engineering

BMS College of Engineering, Bangalore

CGPA 8.17

Skills

The tools I reach for to take an idea from notebook to production.

Languages

  • Python
  • Java
  • JavaScript/TypeScript
  • C
  • C++

AI/ML

  • TensorFlow
  • PyTorch
  • Scikit-learn
  • XGBoost
  • Keras
  • MLflow

NLP & GenAI

  • Transformers
  • BERT
  • RAG
  • Prompt Engineering
  • Claude API
  • LangChain
  • SSE Streaming

Data

  • NumPy
  • Pandas
  • Matplotlib
  • SciPy
  • OpenCV
  • DuckDB
  • SDV

Backend

  • Spring Boot
  • FastAPI
  • REST APIs
  • Microservices
  • WebSockets
  • MySQL
  • MongoDB
  • Node.js

Cloud & DevOps

  • AWS
  • GCP
  • Azure
  • Terraform
  • IaC
  • Docker
  • Jenkins
  • CI/CD
  • GitHub Actions
  • Render
  • Vercel

Testing

  • JUnit
  • pytest
  • Cross-validation
  • Test Automation
  • Text-to-SQL Eval

Tools

  • Git
  • Jira
  • PowerBI
  • Tableau
  • Jupyter
  • Recharts

Publication

Peer-reviewed research, presented at an international conference.

Conference Paper

Supplier Stock Movements as Predictors of Tesla's Stock Price: A Stacking Ensemble Approach

Ohrid Conference, via SRH University of Berlin

A stacking ensemble model that combines LSTM and Random Forest predictions in an XGBoost meta-learner to explore how supplier stock movements relate to Tesla's stock price.

View Code & Paper

Let's Work Together

Hiring, collaborating, or just curious about a project? Say hi.

What I can help you with

LLM & GenAI Applications

RAG pipelines, prompt engineering, eval harnesses, and Claude API integrations that make it to production.

Backend & APIs

FastAPI and Spring Boot services, RESTful APIs, microservices, and real-time WebSocket/SSE systems.

Cloud & Infrastructure-as-Code

Terraform, AWS/GCP/Azure, GitHub Actions with OIDC, Docker, and CI/CD pipelines.

Data & NLP Pipelines

Document classification, information extraction, analytics, and synthetic data with fidelity metrics.

I'm actively looking for Werkstudent, internship, and full-time AI/ML & software roles in Germany. If you're hiring, or just want to talk LLMs, backend systems, or infrastructure, my inbox is open.

Say Hello
GitHubLinkedInBerlin, Germany