Behsad Riemer
about me
i'm a German-American computer science student at TUM. i have built tools at companies in various stages with up to 20M+ users and am generally excited by the challenges that reliability pose. My current interests are: ML engineering + infra, and reliability engineering.
while i've grown to become a big fan of golang, I believe in technology-agnostic engineering by choosing tools for their suitability and strengths.
a non-exhaustive list of technologies I have however worked with include: Golang, TypeScript (NodeJS, Apollo, GraphQL, Next, tRPC, Prisma, React, Tailwind), Python (FastAPI, PyTorch) and Java (Spring Boot).
i also absolutely love speed-house and groove music.
experience
- Implemented an end-to-end ETL pipeline processing 150,000+ entries corresponding to 40,000+ compound discoveries documented in the Materials Project.
- Refactored the dataloading pipeline, reducing material system graph retrieval times from ~30s to <0.5s.
- Designed training loops in PyTorch Geometric using Graph Convolutional Networks (GCNs) to represent material systems as graph objects derived from phase diagrams and formation enthalpies.
- Implemented a simple factory pattern to traverse thousands of entries for the creation of a graph, using a SOTA embeddings model as node features.
- Owned entire implementation, observability and OKR tracking of an ai-summary feature garnering the highest retention (as of 06/2025) with > 25,000 uses after 7 days of launch.
- Integrated extraction and re-insertion of images into AI-driven summaries during on-the-fly streaming with embedded latex rendering for over 4+ file formats (PDF, Word, etc.).
- Planned improvements and evaluated reliability of an in-house AI gateway handling 10,000+ daily requests using retry-logic and fallback logic between various providers.
- Used React, Node.js, MongoDB and GraphQL to enable data aggregation in Earth's largest car simulation center.
- Built a full-stack feature to persist 70+ data points on car simulation studies for 100+ researchers.
- Automated 100% of issue creation and formatting for car simulation studies using the Jira API.
- Led the development of a modular Next.js platform to track and review approximately 400 applicants across multiple phases for events, such as our client-funded consulting services with partners like Google and Microsoft.
- Aided in designing the API using Next.js endpoints which are used to persist 1000+ reviewer notes on potential candidates.
- Dockerized and designed a PostgreSQL database with Prisma, integrated OAuth, and outlined RBAC features.
- Nominated and selected for the internal talent pool program fostering high-performing student employees.
- Used Docker-in-Docker to periodically update dependencies in over 50 repositories using Renovate.
- Decreased PHPStan errors by 50% and 70%, respectively in two internal repositories.
- Refactored 15% of the codebase to support PHP 8.2 and increased unit test coverage by 40% in two repositories.
projects and honors
Literature Review: LLM-Powered Bug Replay
Wrote an exhaustive evaluation and summary of the ICSE paper, "Prompting Is All You Need: Bug Replay with LLMs" by Feng and Chen (2023). Proposed latency and accuracy improvements for programmatic bug replay using LLMs, earning the highest grade (1.0).
Winner of the UnternehmerTUM Innovation Sprint 2024
The innovation sprint is a week-long design-thinking challenge with 250+ participants, offered by UnternehmerTUM and industry partners. My team and I won the "Mobility" track by TUM Venture Labs, solving the issue of limited parking spaces. Pitched to an audience of 300+ people and got offered 4 digit funding.
Organizer of Women in Tech Coding Workshop
Led a three-day coding workshop during Covid-19, promoting STEM engagement among young women between the ages of 12 and 14. In pursuit of this, we incentivized collaboration between girls and boys in a gamified format.
Invenus: A Night Club Ticket Sales Platform
Before Resident Advisor was popular, we collaborated in a team of five to create a full-stack application for selling night club tickets. My responsibilities were making basic API calls in JavaScript, understanding CORS and creating component-based web-pages for viewing event feeds, event pages and confirmation e-mails. We managed the CI/CD processes with Docker.
Research Paper on Pathfinding Algorithms
In high school, I authored a paper with reflection process, analyzing time efficiency of various graph algorithms such as A* Search. The paper earned an 'A' (Scale: A, B, C, D, E) and was selected by the computer science department as an exemplar of outstanding research.