curriculum vitae

education

experience

  • Game rules and localization management.

    • Audited speech datasets and created tooling to measure and report available audio per language

    • Built a reusable script to calculate total duration and file count across dozens of language corpora

    • Fine-tuned a Wav2Vec2 model for Turkmen using Common Voice data, including tokenizer reconstruction and evaluation

    • Collaborated to identify gaps in multilingual AI resources for underrepresented languages

    • Created SDK integration documentation using Markdown

    • Developed and enforced documentation style guidelines across 50+ assets

    • Implemented docs-as-code strategy via Azure DevOps for version control

    • Produced technical mechanic and driver manuals for Volvo Cars & Buses

    • Enhanced Fault Tracing and Diagnostics content with XML tools

    • Adapted documentation for global markets

    • Authored UX copy, game specs, help files, and paytables using XML and DITA

    • Led localization workflows and post-translation editing as de-facto linguist and translation project manager

    • Wrote marketing copy in collaboration with marketing graphic artist.

skills

    • Information architecture

    • Usability testing (heuristic evaluation, card sorting)

    • UX writing & microcopy

    • Content strategy & structured documentation (DITA/XML, Arbortext, Oxygen XML, Markdown docs-as-code)

    • Technical editing, proofreading, release notes, onboarding guides

    • API / SDK documentation

    • Accessibility-focused writing & docs structure

    • Project management (Agile/Scrum, content delivery pipelines)

  • Project management of 29-language game localization (iGaming)

    Academic background in German and Japanese (2 years each)

    Handling large, multilingual corpora (low-resource languages)

    • Data mining & discovery (incl. R workflows)

    • Quantitative analysis & heuristic evaluation (Content Strategy project @ ASU)

    • Annotation & corpus building (low-resource audio/text corpora, multilingual datasets)

    • Error analysis, data cleaning, post-processing OCR outputs

    • Experiment design & evaluation (WER testing, tokenizer comparison, cross-lingual matching)

  • Languages & Libraries:

    • Python, R, PERL, Markdown, Jupyter, NLTK, SpaCy, Scikit-learn, NumPy, Pandas

    Deep Learning / ML Frameworks:

    • PyTorch, TensorFlow, Hugging Face Transformers, NVIDIA NeMo

    • Fine-tuning Wav2Vec2 and Transformer-based ASR models

    • Tokenizer construction (including low-resource orthographies)

    • CTC training and evaluation (WER/CER)

    • Turkmen ASR (WER improved from 0.62 → 0.162)

    • Swedish ASR fine-tuning on Common Voice

    • TTS training (NST Swedish TTS dataset, Coqui/NVIDIA NeMo pipelines)

    • Docker

    • Kubernetes

    • Slurm HPC scheduling

    • Singularity

    • Azure DevOps

    • Git / GitHub

    • Transformer fine-tuning

    • Tokenization

    • Text classification

    • Statistical modeling

    • Classification tasks

    • OCR post-processing (diacritics/character correction)

    • Cross-lingual embeddings

    • Authorship verification

    • Agile/Scrum team collaboration

    • Peer reviews & documentation quality control

    • Cross-functional communication (engineers, product, SMEs, translators, et. al.)

    • Research writing & academic documentation

    • Learning complex systems