Jan is available for hire
Hire JanJan Krepl
Verified Expert in Engineering
Machine Learning Engineer and Developer
Geneva, Switzerland
Toptal member since July 14, 2023
Bio
Jan is a lead machine learning (ML) engineer with expertise in cloud architecture, full-stack development, and freelance software engineering across diverse projects. He designs and deploys machine learning solutions with a strong focus on natural language processing, computer vision, and time series analysis, and seamlessly embeds them into full-stack applications. Outside work, Jan contributes to open-source projects and shares technical knowledge through educational content.
Portfolio
Swiss Tech Startup
Agentic AI, AI SDK, React, Next.js, FastAPI, OpenAI API, AI Chatbots, Terraform...
Software Agency
Large Language Models (LLMs), Agentic AI, Agentic Frameworks, Multimodal Models...
Software Company
Large Language Models (LLMs), Pgvector, Django, Django REST Framework, Celery...
Experience
- Python - 9 years
- Machine Learning - 7 years
- Natural Language Processing (NLP) - 7 years
- Deep Learning - 6 years
- Machine Learning Operations (MLOps) - 5 years
- Amazon Web Services (AWS) - 5 years
- PyTorch - 5 years
- Large Language Models (LLMs) - 4 years
Preferred Environment
Python, Machine Learning, Notion, MongoDB, Amazon Web Services (AWS)
The most amazing...
...thing I've developed is a question-answering tool extracting knowledge from scientific papers.
Work Experience
Senior Machine Learning Engineer
2025 - PRESENT
Swiss Tech Startup
- Led a team of two ML engineers. Designed and implemented all the major features.
- Worked on the full-stack implementation of an AI chatbot with a tool calling connecting to internal APIs.
- Developed an MCP server with custom sandbox code execution logic.
Technologies: Agentic AI, AI SDK, React, Next.js, FastAPI, OpenAI API, AI Chatbots, Terraform, AWS ECS Fargate, TypeScript, PostgreSQL, Docker Compose, Model Context Protocol (MCP), Redis, Amazon S3 (AWS S3), AI Agents, Claude Code
ML Engineer (via Toptal)
2026 - 2026
Software Agency
- Built end-to-end image similarity search API (FastAPI + multimodal LLM embeddings + pgvector HNSW) with a React front end.
- Built a distributed scraping and ingestion pipeline. Celery/Redis workers scrape catalog metadata and images, store media in S3, generate multimodal LLM embeddings, and index records in PostgreSQL.
- Provisioned production AWS infrastructure with Terraform. ECS Fargate (API + workers), RDS with pgvector and tuned HNSW halfvec indexing.
Technologies: Large Language Models (LLMs), Agentic AI, Agentic Frameworks, Multimodal Models, Embedding Models, PostgreSQL, Pgvector, Amazon S3 (AWS S3), Celery, Terraform, Redis, Amazon ElastiCache, FastAPI, Vector Search, AWS ECS Fargate
Machine Learning and Back-end Engineer (via Toptal)
2025 - 2026
Software Company
- Implemented internal document RAG pipeline using technologies like pgvector and Azure Document Intelligence and.
- Integrated inside a Django back end (DRF, Postgres, Celery) and deployed in Azure (Container Apps).
- Implemented multiple document comparison pipelines, including agentic AI approaches.
Technologies: Large Language Models (LLMs), Pgvector, Django, Django REST Framework, Celery, OpenAI, Document Processing, Azure, PostgreSQL, Azure AI Document Intelligence, Claude Code
Experienced AI Developer (via Toptal)
2025 - 2025
Creative Tech Firm
- Designed and built a Python MCP server, enhancing the creative process.
- Stored relevant data in a knowledge graph using Neo4j.
- Shipped the MCP server as a Python package and the whole infrastructure via Docker Compose.
Technologies: Python, Artificial Intelligence (AI), Model Context Protocol (MCP), OpenAI, OpenAI API, Railway, AI Research, Neo4j, Knowledge Graphs, Docker Compose, Cursor AI, FastAPI, AI Agents, Agentic AI
RAG Full-stack Developer (via Toptal)
2025 - 2025
Construction Company
- Built a full-stack application with RAG functionalities that help fill out forms (looking for new clients, internal procedures, etc.).
- Deployed on AWS using Terraform and Terragrunt while keeping complexity low.
- Advised on best practices and documented all the work.
Technologies: Retrieval-augmented Generation (RAG), Natural Language Processing (NLP), Machine Learning, Data Science, FastAPI, Next.js, React, Amazon Web Services (AWS), Terraform, Terragrunt, TypeScript, Python 3, Python, Vector Search, Large Language Models (LLMs), OpenAI
Machine Learning Section Manager | Blue Brain Project
2022 - 2025
The EPFL
- Designed a literature search system focused on semantic search, question answering, named entity recognition, and entity linking, built on top of recent large language models. The entire system was deployed at scale with Kubernetes and AWS.
- Managed a team of four experienced machine learning engineers.
- Acted as a lead developer enforcing best practices.
Technologies: Python, CI/CD Pipelines, BERT, PyTorch, Elasticsearch, Natural Language Processing (NLP), Amazon Web Services (AWS), Machine Learning Operations (MLOps), Deep Learning, Machine Learning, Docker, Unit Testing, REST APIs, FastAPI, GitLab, GitHub, NumPy, Kubernetes, Vim Text Editor, Shell Scripting, SQL, SpaCy, Agile Software Development, Data Science, Orchestration, Computer Vision, Data Versioning, Apache Airflow, LangChain, TensorBoard, Hugging Face Transformers, Git, Generative Pre-trained Transformers (GPT), ChatGPT, OpenAI GPT-4 API, Artificial Intelligence (AI), Hugging Face, APIs, JavaScript, Product Consultant, Natural Language Understanding (NLU), Algorithms, Back-end Development, Language Models, Amazon S3 (AWS S3), Amazon EC2, AWS Glue, Terraform, Pytest, GitLab CI/CD, Large Language Models (LLMs), Redis, Redis Cache, Technical Leadership, Leadership, Retrieval-augmented Generation (RAG), OpenAI, NoSQL, Back-end, Asyncio, Containerization, Python Asyncio, Test-driven Development (TDD), AWS Lambda, REST, Serverless, SDKs, Pinecone, Cloud, CSS, Vector Search, AI Agents, AI Chatbots
Back-end Developer, AI Engineer, Cloud Architect (via Toptal)
2024 - 2024
AI Infrastructure Company
- Built an automated knowledge graph generation back end (FastAPI). Used various vector databases and LLMs.
- Built a Python SDK for the back-end API that was focused on developers.
- Deployed the back end on AWS using Terraform and Terragrunt.
- Implemented unit and integration tests covering the essential functionalities.
Technologies: Python, SDKs, Pinecone, LangChain, Pytest, Httpx, Neo4j, Cypher, Amazon Web Services (AWS), Amazon API Gateway, Entity Component System (ECS), Amazon S3 (AWS S3), Terraform, Terragrunt, MongoDB, MongoDB Atlas, LocalStack, Auth0, Celery, AWS ALB, Pydantic, Semantic Search, Vector Databases, Large Language Models (LLMs), OpenAI
Senior Data Scientist (via Toptal)
2024 - 2024
Innovative Financial Services Company
- Advised on optimal code structure and back-end development.
- Advised on AWS Lambda best practices and optimizations.
- Advised on ML-related topics (pandas and scikit-learn).
Technologies: Machine Learning, Python, Machine Learning Operations (MLOps), Amazon Web Services (AWS), AWS Lambda, Docker, Python 3, Pandas, Scikit-learn
ML Developer (via Toptal)
2024 - 2024
Biotech Company
- Onboarded an open-source (BERT-like) model to the client's platform.
- Advised on best practices (Python, FastAPI, and back-end).
- Advised on best practices (machine learning and deep learning).
Technologies: Machine Learning, Python, Docker, PyTorch, FastAPI, Containerization, Generative Pre-trained Transformers (GPT), Google Cloud Platform (GCP), Kubernetes, Google Kubernetes Engine (GKE), Pytest, Hugging Face Transformers, Ray, Ray Serve, Git
Senior AI Developer (via Toptal)
2023 - 2024
Technology Company at the Intersection of AI, Design, and Science
- Built the back end with FastAPI. Added many LLM wrapper endpoints that integrated with internal data.
- Performed ETL on web scraping datasets and made it available via the back end.
- Handled deployment on AWS (EC2, S3) using Terraform (IaC).
Technologies: Natural Language Processing (NLP), Machine Learning, PyTorch, Python, Amazon Web Services (AWS), Terraform, Amazon S3 (AWS S3), Amazon EC2, Git, OpenAI API, OpenAI SDK, FastAPI, Pydantic, OpenAI, Large Language Models (LLMs)
Data Scientist (via Toptal)
2023 - 2023
Private Trading Firm
- Turned POC Jupyter notebooks into a production-grade Python package. The code backtests a trading algorithm given some parameters.
- Implemented hyperparameter search using Optuna, which allowed us to find the optimal trading parameters.
- Generated Weights & Biases dashboards that helped with feature selection and hyperparameter optimization.
Technologies: Machine Learning, Python, Deep Learning, Trading, Automated Trading Software, Algorithmic Trading, Quantitative Analysis, Scikit-learn, Optuna, Pytest, Jupyter Notebook, Data Classification, Weights & Biases
Senior NLP Developer (via Toptal)
2023 - 2023
US Research Institution
- Optimized and deployed a custom sentiment analysis model (based on BERT) on AWS (SageMaker).
- Wrote a full FastAPI back end for a web application and deployed it on AWS. Collaborated with a React front-end developer to deliver the web application—a standard three-tier web application with extra ML model inference endpoints.
- Contributed to batch model inference on internal data together with LLM APIs. Made data available via the back end.
Technologies: Natural Language Processing (NLP), Machine Learning, PyTorch, Python, Amazon Web Services (AWS), Hugging Face Transformers, FastAPI, Amazon S3 (AWS S3), Amazon EC2, BERT, OpenAI API, Large Language Models (LLMs), Pytest, Pandas, Pydantic, Git, Transformers, OpenAI, Web Scraping
Machine Learning Engineer | Blue Brain Project
2018 - 2022
The EPFL
- Conceived and implemented a supervised algorithm for 2D brain slice image registration that became a part of internal workflows.
- Developed a knowledge extraction pipeline for scientific articles with main functionalities such as parsing, neural search, and named entity recognition.
- Engaged directly in various neuroscientific projects, including neuron-type classification with graph neural networks and morphology image synthesis with generative adversarial networks.
Technologies: CI/CD Pipelines, Python, OpenCV, Keras, PyTorch, Deep Learning, Machine Learning, GitLab CI/CD, Image Registration, SpaCy, Git, Machine Learning Operations (MLOps), REST APIs, FastAPI, GitLab, GitHub, NumPy, Kubernetes, Vim Text Editor, Shell Scripting, SQL, Agile Software Development, Data Science, Orchestration, Natural Language Processing (NLP), Elasticsearch, Docker, Computer Vision, Data Versioning, Apache Airflow, Unit Testing, TensorBoard, Hugging Face Transformers, MySQL, PostgreSQL, Artificial Intelligence (AI), Hugging Face, APIs, Natural Language Understanding (NLU), Generative Pre-trained Transformers (GPT), Algorithms, Back-end Development, Language Models, TensorFlow, Pytest, Large Language Models (LLMs), NoSQL, Back-end, Asyncio, Containerization, Python Asyncio, Test-driven Development (TDD), Cloud
Data Scientist
2018 - 2018
Nectar Financial
- Enhanced internal portfolio optimization algorithms with return forecasting using supervised learning techniques. Added custom constraints and objective functions, making the tool more flexible.
- Applied text embedding algorithms, such as Doc2Vec and TF-IDF, on hedge fund fact sheets and reports. In turn, these embeddings were used for clustering, which allowed for better diversification.
- Developed a custom back-testing framework considering various hedge-fund-specific constraints like lock-ups.
Technologies: Python, Machine Learning, Deep Learning, Gensim, Scikit-learn, Pandas, NumPy, Jupyter Notebook, SciPy, StatsModels, SpaCy, REST APIs, GitHub, SQL, Data Science, Natural Language Processing (NLP), Keras, Docker, Time Series Analysis, Unit Testing, Git, Artificial Intelligence (AI), JavaScript, Algorithms, Back-end Development, Pytest, NoSQL, Test-driven Development (TDD)
Quantitative Risk Analyst
2016 - 2017
UBS
- Maintained the Lombard lending section's stress-testing codebase that used Visual Basic, SQL, and SAS.
- Generated regular risk reports used as inputs for other departments.
- Supported senior analysts in creating custom risk models.
Technologies: SQL, Shell Scripting, Probability Theory, Time Series Analysis, Algorithms, NoSQL
Experience
Mildlyoverfitted | Educational Videos
https://www.youtube.com/@mildlyoverfitted/A YouTube channel that I developed to host educational content and resources. The channel features videos I've created on machine learning, deep learning, and Python. One of the main goals is to explain how things work under the hood and how we can implement solutions from scratch.
Spectamoments
https://spectamoments.comA full-stack event photography platform: photographers upload event galleries, participants browse and buy photos via Stripe, and Celery workers handle async image processing. A CV/LLM pipeline detects bib numbers to auto-match photos to participants.
DeepDow | Portfolio Optimization with Deep Learning
https://github.com/jankrepl/deepdow/A Python package for portfolio optimization with deep learning. It attempts to merge the following two very common steps in portfolio optimization:
• Forecasting the market's future evolution, such as long short-term memory networks (LSTM) and generalized autoregressive conditional heteroskedasticity (GARCH).
• Providing optimization problem designs and solutions, such as convex optimization.
It does so by constructing a pipeline of layers. The last layer performs the allocation, and all the previous ones serve as feature extractors. The overall network is fully differentiable, and one can optimize its parameters by gradient descent algorithms.
• Forecasting the market's future evolution, such as long short-term memory networks (LSTM) and generalized autoregressive conditional heteroskedasticity (GARCH).
• Providing optimization problem designs and solutions, such as convex optimization.
It does so by constructing a pipeline of layers. The last layer performs the allocation, and all the previous ones serve as feature extractors. The overall network is fully differentiable, and one can optimize its parameters by gradient descent algorithms.
MLtype | Command Line Tool
https://github.com/jankrepl/mltype/A programmer-friendly command line tool for improving typing speed and accuracy. The main goal is to help programmers practice programming languages. It uses neural networks to generate text. One can go for pre-trained networks or train new ones from scratch.
Atlas Alignment | Multimodal Registration and Alignment
https://github.com/BlueBrain/atlas-alignment/A toolbox to perform multimodal image registration, which includes traditional and supervised deep learning models. This project originated from the Blue Brain Project efforts on aligning mouse brain atlases obtained with in situ hybridization (ISH) gene expression and Nissl stains. The project was published on Frontiers Media, which you can access via this link: frontiersin.org/articles/10.3389/fninf.2021.691918/full/
PyChubby | Automated Face-warping Tool
https://github.com/jankrepl/pychubby/A Python package for automated face warping. It allows the user to programmatically change the facial expression and shape of any person in an image. It is based on geometric transformations using computer vision.
Distortion Catcher
Distortion Catcher is a web platform designed to help users identify automatic thoughts and analyze them with the help of AI. It analyzes your thoughts and suggests personalized coping strategies to challenge cognitive distortions.
Education
2015 - 2018
Master's Degree in Quantitative Finance
ETH Zurich - Zurich, Switzerland
2011 - 2014
Bachelor's Degree in Economics
Charles University - Prague, Czechia
Certifications
AUGUST 2026 - AUGUST 2027
Claude Certified Developer - Foundations
Anthropic
AUGUST 2026 - AUGUST 2027
Claude Certified Architect - Foundations
Anthropic
APRIL 2025 - PRESENT
Microsoft Certified: Azure Fundamentals
Microsoft
JUNE 2024 - JUNE 2027
AWS Certified Solutions Architect - Professional
Amazon Web Services
FEBRUARY 2024 - FEBRUARY 2026
HashiCorp Certified: Terraform Associate (003)
HashiCorp
JANUARY 2024 - JANUARY 2027
AWS Certified Solutions Architect - Associate
Amazon Web Services
SEPTEMBER 2023 - SEPTEMBER 2025
Google Cloud Certified Professional Machine Learning Engineer
Google Cloud
AUGUST 2023 - AUGUST 2026
AWS Certified Machine Learning - Specialty
Amazon Web Services
JUNE 2023 - JUNE 2025
Databricks Certified Associate Developer for Apache Spark 3.0
Databricks Inc.
MARCH 2023 - MARCH 2026
AWS Certified Cloud Practitioner
Amazon Web Services
FEBRUARY 2023 - FEBRUARY 2026
CKAD: Certified Kubernetes Application Developer
The Linux Foundation
JANUARY 2023 - PRESENT
Professional Scrum Master (PSM I)
Scrum.org
JULY 2015 - PRESENT
CFA Level I (Passed)
CFA Institute
Skills
Libraries/APIs
PyTorch, Scikit-learn, NumPy, Keras, Hugging Face Transformers, SciPy, Pandas, Matplotlib, REST APIs, TensorFlow, Asyncio, Python Asyncio, OpenAI API, Amazon Rekognition, Claude API, JAX, React, React Query, Stripe, OpenCV, SpaCy, Terragrunt, Pydantic, Ray Serve
Tools
Vim Text Editor, Git, GitLab CI/CD, Pytest, TensorBoard, GitLab, GitHub, ChatGPT, Notion, Amazon SageMaker, Cloud Dataflow, Google Compute Engine (GCE), AWS Glue, Terraform, Claude Code, Claude, Inkscape, Apache Airflow, Auth0, Amazon Cognito, Adobe Premiere Pro, Seaborn, Gensim, StatsModels, Scikit-image, Google Kubernetes Engine (GKE), Amazon Elastic Container Service (ECS), MongoDB Atlas, Celery, Docker Compose, Amazon ElastiCache, AI SDK
Languages
Python, JavaScript, TypeScript, CSS, SQL, Python 3, Cypher
Paradigms
Unit Testing, Test-driven Development (TDD), REST, Scrum, Agile Software Development, Entity Component System (ECS), Model Context Protocol (MCP)
Platforms
Kubernetes, Docker, Amazon Web Services (AWS), Jupyter Notebook, Vertex AI, Amazon EC2, Google Cloud Platform (GCP), AWS Lambda, AWS ALB, Azure, Weights & Biases, LocalStack
Storage
Elasticsearch, PostgreSQL, Google Cloud Storage, Amazon S3 (AWS S3), Redis, Redis Cache, NoSQL, Neo4j, MongoDB, MySQL
Frameworks
Next.js, Tailwind CSS, Apache Spark, Optuna, Ray, Django, Django REST Framework, Agentic Frameworks
Other
Probability Theory, Mathematical Analysis, Statistics, Machine Learning, Portfolio Optimization, Orchestration, Machine Learning Operations (MLOps), Shell Scripting, Generative Pre-trained Transformers (GPT), BERT, Natural Language Processing (NLP), FastAPI, Open Source, Finance, Data Science, Computer Vision, OpenAI GPT-4 API, Artificial Intelligence (AI), Hugging Face, APIs, Natural Language Understanding (NLU), Algorithms, Back-end Development, Language Models, Pub/Sub, Full-stack Development, Large Language Models (LLMs), Technical Leadership, Leadership, Retrieval-augmented Generation (RAG), OpenAI, Back-end, Containerization, Serverless, SDKs, Pinecone, Cloud, FAISS, Vector Search, AI Agents, AI Chatbots, Optimization, Microeconomics, Macroeconomics, Mathematical Finance, Quantitative Risk Analysis, Numerical Methods, MLflow, LangChain, Time Series Analysis, Product Consultant, Vite, Full-stack, Web Scraping, Econometrics, Deep Learning, Scrum Master, CI/CD Pipelines, Online Course Design, Recurrent Neural Networks (RNNs), Image Registration, Data Versioning, Google BigQuery, Text-to-text Transfer Transformer (T5), Trading, Automated Trading Software, Algorithmic Trading, Quantitative Analysis, Data Classification, OpenAI SDK, Transformers, Httpx, Amazon API Gateway, Semantic Search, Vector Databases, Railway, AI Research, Knowledge Graphs, Cursor AI, Agentic AI, Pgvector, Document Processing, Multimodal Models, Embedding Models, AWS ECS Fargate, Azure AI Document Intelligence
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring