Senior AI Engineer Deploy Staff

## WHAT WE EXPECT

Our core stack is Python, Django, Angular, and RAG/LLM-based workflows.

This is our core technology stack and is non-negotiable. We are looking for someone who is already strong in these areas and can contribute productively from the start.

## CORE REQUIREMENTS

1. Production LLM / RAG experience

You have built and operated production LLM systems, including areas such as:

• RAG and retrieval design
• Chunking and document processing
• Structured data extraction
• Evaluation of LLM outputs
• Agentic or multi-step LLM workflows

We are specifically looking for experience beyond prototypes. You should have shipped systems to real users and dealt with the issues that only appear once they are running in production.

2. Python, Django and PostgreSQL

Strong Python experience is required, together with Django and/or Django REST Framework.

You should be comfortable designing PostgreSQL data models, debugging backend issues, and operating systems in production.

3. Angular and TypeScript

You will own the frontend of the features you build.

You therefore need to be able to implement and ship features independently in Angular and TypeScript without waiting for another frontend developer.

We expect experience from at least 1-2 production Angular projects.

4. English

Advanced English, approximately C1 level.

You will work directly with senior, often non-technical stakeholders. You need to be able to ask precise questions, challenge assumptions, explain technical decisions clearly, and explain something differently when the first explanation does not land.

## ALSO PART OF THE WORK

You will encounter all of the following.

We do not expect equal depth in every area, but we do expect you to be able to learn quickly and take ownership where your experience is currently lighter.

• Celery, Redis, queues and asynchronous processing
• Enterprise integrations with ERP, finance and CRM systems and their APIs
• Cloud infrastructure, deployment, observability and security
• AWS and/or GCP
• Kubernetes and Docker
• Understanding an existing system before changing it
• Improving systems without unnecessarily replacing parts that already work

## WHAT MATTERS MORE THAN THE CV

We care about what YOU personally built, what YOU personally decided, and what happened when something broke.

During the interview, we will want to understand:

• What you personally implemented
• Which architectural or technical decisions you made
• Why you made those decisions
• What failed or caused problems
• How you diagnosed and fixed it
• What you would do differently now

If your strongest examples are systems that your team implemented while you mainly supervised the work, this is probably not the right role.

To highlight this again: Python, Django, Angular, and production RAG/LLM experience are our core requirements. We cannot compromise on this stack.

## HOW WE WORK

Remote.

Working hours should have good overlap with Ukraine / EU business hours.

We are a small team with direct access to decision makers and real operational problems to solve.

You will usually receive a problem to solve rather than a detailed specification to implement.

We expect you to understand the problem, question requirements where necessary, propose a solution, and take it through implementation and production.

## INTERVIEW PROCESS

1. Fill out a Form with your Basic information and expectations - https://forms.gle/hzLfnHWBreAn6Cbb8 2. Introductory interview 3. Technical interview with our team 4. Test task 5. Offer

Interviews are recorded and shared only within the hiring team.

This allows hiring decisions to be based on what candidates actually said during the interview rather than on someone else's notes or interpretation.