Jan Krepl
Verified Expert in Engineering
Machine Learning Engineer and Developer
Jan是一位对软件工程充满热情的机器学习工程师, machine learning, leadership, and online education. 他在应用计算机视觉方面有丰富的专业经验, natural language processing, 以及在学术和商业环境中的时间序列分析. 他还将大部分空闲时间用于开源软件和教育内容创作.
Portfolio
Experience
Availability
Preferred Environment
Python, Machine Learning, Notion
The most amazing...
...我开发了一个从科学论文中提取知识的问答工具.
Work Experience
机器学习部门经理|蓝脑项目
The EPFL
- 设计了一个以语义检索为核心的文献检索系统, question answering, named entity recognition, and entity linking, 建立在最近的大型语言模型之上. 整个系统通过Kubernetes和AWS大规模部署.
- 管理一个由四名经验丰富的机器学习工程师组成的团队.
- 作为执行最佳实践的首席开发人员.
机器学习工程师|蓝脑计划
The EPFL
- 构思并实现了一种2D脑切片图像配准的监督算法,该算法成为内部工作流程的一部分.
- 开发了一个科学文章的知识抽取管道,主要功能有解析等, neural search, and named entity recognition.
- 直接参与各种神经科学项目, 包括用图神经网络进行神经元类型分类和用生成对抗网络进行形态学图像合成.
Data Scientist
Nectar Financial
- 增强内部投资组合优化算法与回报预测使用监督学习技术. 增加了自定义约束和目标函数,使工具更加灵活.
- 应用文本嵌入算法,如Doc2Vec和TF-IDF,在对冲基金的情况说明书和报告. 反过来,这些嵌入被用于聚类,这允许更好的多样化.
- 考虑到各种对冲基金特定的限制,如锁定期,开发了一个定制的后台测试框架.
Quantitative Risk Analyst
UBS
- 使用Visual Basic维护Lombard贷款部门的压力测试代码库, SQL, and SAS.
- 定期生成风险报告,作为其他部门的输入.
- 支持高级分析师创建自定义风险模型.
Experience
Mildlyoverfitted | Educational Videos
http://www.youtube.com/@mildlyoverfitted/DeepDow |深度学习组合优化
http://github.com/jankrepl/deepdow/• Forecasting the market's future evolution, 如长短期记忆网络(LSTM)和广义自回归条件异方差(GARCH)。.
•提供优化问题的设计和解决方案,如凸优化.
它通过构造一个层的管道来实现. 最后一层执行分配,前面的所有层都作为特征提取器. 整个网络是完全可微的, 并且可以通过梯度下降算法对其参数进行优化.
MLtype | Command Line Tool
http://github.com/jankrepl/mltype/Atlas对准|多模态配准与对准
http://github.com/BlueBrain/atlas-alignment/PyChubby | Automated Face-warping Tool
http://github.com/jankrepl/pychubby/Skills
Languages
Python, SQL, SAS, Excel VBA, JavaScript
Libraries/APIs
PyTorch, Scikit-learn, NumPy, Keras, SciPy, Pandas, Matplotlib, REST APIs, TensorFlow, OpenCV, SpaCy, React
Tools
Vim Text Editor, Git, GitLab CI/CD, Pytest, TensorBoard, GitLab, GitHub, Notion, Amazon SageMaker, Cloud Dataflow, Google Compute Engine (GCE), AWS Glue, Inkscape, Apache Airflow, Adobe Premiere Pro, Seaborn, Gensim, StatsModels, Scikit-image, Google Kubernetes Engine (GKE), Terraform
Paradigms
单元测试,数据科学,Scrum,敏捷软件开发
Platforms
Kubernetes, Docker, Jupyter Notebook, Amazon EC2, Amazon Web Services (AWS)
Storage
Elasticsearch, Google Cloud Storage, Amazon S3 (AWS S3), MySQL, PostgreSQL
Other
Probability Theory, Mathematical Analysis, Linear Algebra, Statistics, Machine Learning, Portfolio Optimization, Orchestration, Machine Learning Operations (MLOps), Shell Scripting, Generative Pre-trained Transformers (GPT), BERT, Hugging Face Transformers, Sphinx, Natural Language Processing (NLP), Computer Vision, ChatGPT, OpenAI GPT-4 API, Artificial Intelligence (AI), Hugging Face, APIs, Regular Expressions, Natural Language Understanding (NLU), GPT, Algorithms, Back-end Development, Language Models, Vertex AI, Pub/Sub, Optimization, Microeconomics, Macroeconomics, Mathematical Finance, Quantitative Risk Analysis, Numerical Methods, Jax, MLflow, FastAPI, LangChain, Time Series Analysis, Product Consultant, Measure Theory, Econometrics, Private Company Valuation, Deep Learning, Scrum Master, CI/CD Pipelines, Online Course Design, Recurrent Neural Networks (RNNs), Open Source, Finance, Image Registration, Data Versioning, Google BigQuery, Full-stack Development
Frameworks
Apache Spark
Education
Master's Degree in Quantitative Finance
ETH Zurich - Zurich, Switzerland
Bachelor's Degree in Economics
Charles University - Prague, Czechia
Certifications
AWS认证解决方案架构师-助理
Amazon Web Services
谷歌云认证专业机器学习工程师
Google Cloud
AWS Certified Machine Learning - Specialty
Amazon Web Services
Databricks认证的Apache Spark 3助理开发人员.0
Databricks Inc.
AWS Certified Cloud Practitioner
Amazon Web Services
CKAD:认证Kubernetes应用程序开发人员
The Linux Foundation
Professional Scrum Master (PSM I)
Scrum.org
CFA Level I (Passed)
CFA Institute