Navigation überspringen

Maksim Shmalts

Bis 2024, Working Student for LLMs, IAV GmbH
Tübingen, Deutschland

Fähigkeiten und Kenntnisse

Python
Natural Language Processing (NLP)
Large Language Models
Retrieval-Augmented Generation
Data Science
Computational Linguistics
Neural Networks
PyTorch
LangChain
Transformers

Werdegang

Berufserfahrung von Maksim Shmalts

  • 2023 - 2024

    Working Student for LLMs

    IAV GmbH

    • Implemented and integrated a tool for evaluation of LLMs and RAG pipelines (Python, LangChain, Ragas, OpenAI) • Currently, connecting OpenAI function calling to our internal on-premise models (Python, TGI, LangChain)

  • 2022 - 2024

    Tutor / HiWi

    Karl Eberhards Universität Tübingen

    • Held tutorials and contributed into evaluating assignments and projects for the courses "String Algorithms" (WiSe22/23), "Python for Beginners" (WiSe22/23), "Statistical Language Processing II" (SoSe23), "Reinforcement Learning for LLMs" (SoSe24) • Created Finite-States Transducers for measuring distance between German dialects for the course "String Algorithms" (Python, pynini)

  • 2021 - 2023

    Data Scientist / NLP Engineer

    MKSKOM

    • Implemented backend for a custom Llama-2-based RAG Engine for a large customer (Python, LangChain, Llama.cpp, HF Transformers) • Increased the number of responses from potential customers on a freelance platform by 5 times by independently designing and implementing an LLM-based automation tool (Python, LangChain, OpenAI) • Implemented tools for NLP, Time Series Prediction, Optimization Modeling, Data Analysis (Python, PyTorch, spaCy, scikit-learn, statsmodels, Pandas, NumPy, streamlit)

  • 2021 - 2022

    Course Instructor (Linguistics for Olympiades)

    Lomonosov Moscow State University Gymnasium

    • Held lectures, prepared and evaluated assignments for the Course "Linguistics for Olympiads"

  • 2021 - 2022

    Assessor

    Yandex

    • Evaluated search engine results on IT-themed queries, evaluated machine translations

Ausbildung von Maksim Shmalts

  • 2022 - 2024

    Computational Linguistics

    Karl Eberhards Universität Tübingen

    • 2024 (in progress) Bachelor thesis on applying LLMs to solving non-trivial linguistic tasks (on the example of splitting German compounds (Python, LangChain, PyTorch, HF transformers, spaCy) • 2024 Group project on investigating influence of RL fine-tuning data on biasing LLMs (Python, HF transformers) • 2023 Participated at the SemEval 2023 and published a paper at the ACL Anthology (Python, HF transformers)

  • 2019 - 2022

    Theoretical and Applied Linguistics

    Lomonosov Moscow State University

    • 2022 Personal project DERBI: a tool for automatic inflection of German words (Python) • 2022 Conference diploma for DERBI at Lomonosov-2022 (Moscow), Science Sessions-2022 (Kaliningrad), XXII International Conference of Young Slavists (Tallinn) • 2021 Term paper on predicting ablaut class of German strong verbs (Python, PyTorch)

  • 2017 - 2019

    History and Philology

    Lomonosov Moscow State University Gymnasium

    • 2019 Prize-winner of All-Russian Olympiad for Linguistics (gives no-exam admission to the university of choice) • 2019 Graduation with a Gold Medal

Sprachen

  • Englisch

    Fließend

  • Deutsch

    Gut

  • Russisch

    Muttersprache

  • Spanisch

    Grundlagen

XING – Das Jobs-Netzwerk

  • Über eine Million Jobs

    Entdecke mit XING genau den Job, der wirklich zu Dir passt.

  • Persönliche Job-Angebote

    Lass Dich finden von Arbeitgebern und über 20.000 Recruiter·innen.

  • 22 Mio. Mitglieder

    Knüpf neue Kontakte und erhalte Impulse für ein besseres Job-Leben.

  • Kostenlos profitieren

    Schon als Basis-Mitglied kannst Du Deine Job-Suche deutlich optimieren.

21 Mio. XING Mitglieder, von A bis Z