Julian Schnitzler
Software Engineer at GoogleZurich, Switzerland

Julian Schnitzler

ML engineer working between data and modeling — LLM post-training, AI agents, and evaluations at scale.

I'm a Software Engineer at Google in Zurich (YouTube Trust & Safety), where I post-train frontier LLMs for policy-violation detection and build AI agents improved with automatic prompt optimization.

Previously, I worked as an Applied Scientist at 2K Games on real-time ML matchmaking for NBA 2K, as an SDE at Amazon Web Services on distributed ML anomaly detection in CloudWatch, and conducted research and engineering internships at NII Tokyo, Google Zurich, and LinkedIn. I hold an M.Sc. in Data Science from EPFL and a B.Sc. in Computer Science from RWTH Aachen.

LLM Post-TrainingAI Agents & APOEvaluation & DatasetsLarge-Scale Data Pipelines
Julian Schnitzler
01

Selected Projects

Research code, benchmarks & open-source tools

Research2024

InkSight

Offline-to-online handwriting conversion (TMLR): trained PaLI-style vision-language models up to 5B parameters on 64 TPUs (JAX, T5X) using unpaired data, achieving 87% human-validated stroke conversions.

JAX / T5XVision-Language64 TPUsGoogle Research
Research2024

MoreHopQA

Evaluation dataset of 1,118 human-verified multi-hop questions extending existing QA benchmarks with commonsense, arithmetic, and symbolic reasoning—benchmarked across models up to 70B parameters.

PythonNLPLLM EvaluationDataset
Open Source2023–2024

Flows (aiFlows)

Modular conceptual framework and open-source library developed at EPFL for composing, debugging, and scaling structured interactions between autonomous AI agents and humans.

PythonMulti-AgentFrameworkEPFL
Developer Tool2024

roblox-to-github-exporter

A fast CLI utility built with Lune that transforms monolithic Roblox place files (.rbxl / .rbxlx) into clean, diffable directory trees tailored for Git version control and collaborative workflows.

LuauLuneCLIDevTools
02

Publications & Research

Selected preprints and peer-reviewed work

03

Experience & Education

Industry, research labs & academic background

Experience

  1. Software Engineer · Google (YouTube Trust & Safety)

    Aug 2026 — Present

    Zurich, Switzerland

    Post-training Google's frontier LLMs for YouTube policy-violation detection and building an AI video-review agent (prompt, tools, logic) improved with automatic prompt optimization (APO).

  2. Applied Scientist · 2K Games

    Jul 2025 — Jul 2026

    Dublin, Ireland

    Built ML-based matchmaking and skill rating for NBA 2K matching millions of players in real time; analyzed large-scale player data and prototyped new modeling approaches.

  3. Software Development Engineer · Amazon Web Services (AWS)

    Oct 2024 — Jul 2025

    Dublin, Ireland

    Built and maintained a distributed ML anomaly detection system for customer time-series metrics in CloudWatch Alarms (Java, Python); added 2 time-series models driving 22% YoY adoption growth at 99.999% uptime.

  4. NLP Research Intern · National Institute of Informatics (NII)

    Mar 2024 — Aug 2024

    Tokyo, Japan

    Created MoreHopQA (co-first author, 1,118 human-verified multi-hop questions); built dataset pipelines and evaluated/fine-tuned up to 70B-parameter models on multi-GPU clusters.

  5. Student Researcher · Google

    Sep 2023 — Feb 2024

    Zurich, Switzerland

    Co-authored InkSight (TMLR); trained PaLI-style vision-language models up to 5B parameters on 64 TPUs (JAX, T5X) using unpaired training data and an OCR-based evaluation pipeline.

  6. AI Engineering Intern · LinkedIn

    Jun 2023 — Aug 2023

    Dublin, Ireland

    Built an automated evaluation system over datasets up to 100B rows (Spark, Scala), cutting iteration time from days to under an hour; owned prompt design for LinkedIn Premium's GPT-4 Writing Assistant.

Education

  1. M.Sc. in Data Science · EPFL (École Polytechnique Fédérale de Lausanne)

    Sep 2021 — Sep 2024

    Lausanne, Switzerland

    Focus on machine learning, NLP, and large-scale data science; contributed to the Flows collaborative AI framework.

    GPA 5.78/6.00 · Top 5% · Lopez-Loreta Nominee
  2. B.Sc. in Computer Science · RWTH Aachen University

    Oct 2017 — Nov 2020

    Aachen, Germany

    Foundations in computer science, algorithms, and process mining (including open-source contributions to PM4Py).

    GPA 1.0/1.0 · Best Bachelor's Thesis Award

Technical Stack

Languages

PythonJavaKotlinScalaC++SQL

Data & Pipelines

SparkPandasNumPyDataset Construction & FilteringHuman AnnotationStatistics

Deep Learning & LLMs

PyTorchJAX / FlaxTensorFlowHuggingFaceLLM Post-TrainingW&BDockerAWS
04

Contact

Research collaborations, engineering & inquiries

Let's connect.

Whether you want to discuss machine learning research, open-source tooling, or engineering projects, feel free to reach out via email or connect on LinkedIn, X, or GitHub.