AI agents & LLM apps
Assistants, agents and automations on your documents, data and processes. Built on the model that fits, from OpenAI, Claude and Gemini to open models on your own servers, and tested before your users see it.
For recruiters
Two senior engineers. One team.
Data engineering, machine learning and AI solutions, from first idea to production. Here is what we do and how we like to work, so you can match us with the right client.
Recruiters are welcome, and we're flexible on how you earn. Ask the assistant about rates and how we work together.
What we do
Our expertise
Reliable data and reporting
Your scattered sources brought into one place you and your team can trust: pipelines that run on their own, dashboards that agree with each other, and alerts when something breaks.
Machine learning
From problem framing to models in production: forecasting, recommendations, fraud detection, image and text. We start with a baseline and prove the gain with A/B tests.
Tools and portals your team can rely on
Internal tools, customer portals and the product around your data or models, including turning an AI-built prototype into something you can depend on.
Tools we work with · Proven tools, chosen per project.
- AI & LLMs
- LangGraph
- LangChain
- OpenAI API
- Hugging Face
- Local LLMs
- pgvector
- Data
- Python
- SQL
- Airflow
- Databricks
- Spark
- n8n
- Machine learning
- scikit-learn
- TensorFlow
- MLflow
- Web & APIs
- FastAPI
- Flask
- Streamlit
- TypeScript
- Next.js
- PostgreSQL
- Cloud
- AWS
- GCP
- Azure
- Docker
The team
Who your client gets
Both of us work on every project.
Kristof Menyhert
Technical lead
Ideas, architecture, data platforms, ML and LLM engineering. Turns hard problems into systems that keep running.
Juhi Chandra
ML & AI lead · storyteller
Our storyteller in client conversations and presentations, and builds ML and AI that runs in production.
How we work
Project-based first.
We do our best work when we own an outcome together with the client. Other set-ups are possible too.
Preferred
Project
We look at what needs to be done and quote for it, at a fixed price or time and materials, contracted through our company. We help shape the solution and deliver it end to end. Need more hands? We bring in extra people and stay the project lead.
When the work interests us
A role in the team
We size the work and agree on the outcome rather than on days, then work on it as agreed, 1 to 5 days a week depending on the need. Remote works best for us; we come on site from time to time when it helps. Invoiced by our company.
For something special
A permanent job
Not our usual route. But if you have something special in mind, tell us: we're happy to hear it.
Have a role?
What helps us answer quickly
Tell the assistant: it knows how we work with recruiters and can book a call with us.
- The client's sector and the problem to solve
- Scope or deliverables, as far as known
- Duration and hours per week
- Remote, hybrid or on site (and where)
- Start date and contract type