AI Engineer

Univio; Wrocław; On-site; PLN 165,000 - 234,000; Full time

Job summary

Univio is seeking a seasoned backend AI/LLM integration engineer in Wrocław to develop tools based on AI agents, workspaces, and pipelines, and to integrate applications with leading AI models.

You will orchestrate development environments with Docker/Docker Compose, collaborate with DevOps, analysts, and business stakeholders, and help optimize token usage and costs. The role emphasizes security, governance, and scalable AI solutions.

Qualifications

• Experience in developing backend solutions and API integrations.
• Hands-on experience with AI/LLM tools and language models.
• Experience integrating with AI models (OpenAI, Azure OpenAI, Gemini, Claude/Anthropic, or open-source).
• Ability to design AI agent-based solutions and automation pipelines.
• Knowledge of Docker and Docker Compose and setting up dev environments.
• Experience with Git, code reviews, conflict resolution, and maintaining code quality.
• Ability to diagnose issues in applications, logs, databases, and runtimes.
• Understanding CI/CD, containerization, and production testing environments.
• Strong collaboration with DevOps, analysts, and business stakeholders.
• Focus on security, access control, license compliance, and responsible AI use.

Responsibilities

• Developing and maintaining tools based on AI agents, workspaces, prompt configurations, and agent pipelines.
• Integrating applications with LLM models and developing an intermediary layer such as an AI Gateway / proxy / broker.
• Developing the backend of AI applications, including handling import, indexing, and processing of documents (PDF, DOCX, XLSX, CSV, Markdown).
• Building integrations with Jira, SharePoint, Power BI, Grafana, n8n, and databases.
• Preparing and maintaining development environments based on Docker, Docker Compose, containers, and isolated workspaces.
• Collaborating on deployments, application configuration, CI/CD processes, and Kubernetes environments.
• Monitoring the usage of AI models: tokens, costs, requests, metrics, and expanding dashboards in Grafana.
• Testing new AI models, including open-source models, and evaluating their quality, costs, and deployment potential.
• Optimizing the costs of using AI through caching, proxies, prompt compression, and best practices for token usage.
• Refactoring code, conducting code reviews, fixing bugs, and organizing repositories.
• Co-creating and implementing standards for using AI in projects and documenting best practices for the team.

Skills

Backend development

API integration

AI/LLM tools

AI model integrations

AI agents design

Git & code reviews

CI/CD

Security best practices

Tools

Docker / Docker Compose

Kubernetes

Jira

SharePoint

Power BI

Grafana

n8n

Databases

Job description

B2B: 120 - 170 PLN/h
It is also possible to choose a different form of cooperation.
The salary range shown applies to B2B cooperation. If you prefer another form of cooperation, let us know — we’ll be happy to discuss the available options and adjust the terms to the selected model.

• Experience in developing backend solutions and integrating systems via APIs.
• Practical experience with AI / LLM tools, including an understanding of language models, prompts, context, tokens, and cost limitations.
• Experience integrating with AI models such as OpenAI, Azure OpenAI, Gemini, Claude/Anthropic, or open-source models.
• Ability to design and develop solutions based on AI agents, task automation, agent pipelines, or similar mechanisms.
• Knowledge of Docker / Docker Compose and the ability to prepare local or isolated development environments.
• Experience working with Git, code reviews, conflict resolution, refactoring, and maintaining code quality.
• Ability to diagnose technical issues in applications, logs, integrations, databases, and runtime environments.
• Understanding of CI/CD, containerization, and working with testing and production environments.
• Strong collaboration skills when working with development teams, DevOps, analysts, and business stakeholders.
• Focus on security, access control, license compliance, and responsible use of AI tools.

Duties / Your Role

• Developing and maintaining tools based on AI agents, workspaces, prompt configurations, and agent pipelines.
• Integrating applications with LLM models and developing an intermediary layer such as an AI Gateway / proxy / broker.
• Developing the backend of AI applications, including handling the import, indexing, and processing of documents such as PDF, DOCX, XLSX, CSV, and Markdown.
• Building integrations with company tools such as Jira, SharePoint, Power BI, Grafana, n8n, and databases.
• Preparing and maintaining development environments based on Docker, Docker Compose, containers, and isolated workspaces.
• Collaborating on deployments, application configuration, CI/CD processes, and Kubernetes environments.
• Monitoring the usage of AI models: tokens, costs, requests, metrics, and expanding dashboards in Grafana.
• Testing new AI models, including open-source models, and evaluating their quality, costs, and deployment potential.
• Optimizing the costs of using AI through caching, proxies, prompt compression, and best practices for token usage.
• Refactoring code, conducting code reviews, fixing bugs, and organizing repositories.
• Co-creating and implementing standards for using AI in projects and documenting best practices for the team.

Nice / To Have

• Knowledge of Kubernetes, AWS, or Azure.
• Experience with tools such as n8n, Grafana, Power BI, Jira, and SharePoint.
• Experience working with AI agents, tools such as Harness, agent frameworks, or developer workflow automation.
• Experience with open-source models and running them locally or in the cloud.
• Understanding of topics related to optimizing infrastructure costs and token usage.
• Experience with RAG systems, semantic search, knowledge bases, or document processing.
• Experience working on projects requiring compliance, audits, or high security standards.

Good projects need good teams!

We develop practical AI solutions used in internal and commercial projects. We work on AI agents, process automation, LLM integrations, developer tools, cost monitoring, and standards for the safe use of AI within the organization.

Individual approach for every candidate

Every role is different. We respond to the needs of each candidate and the position applied for. This way, you get the best recruitment experience and we get the best team members.

Fast process

Nobody likes waiting around. On average, from initial application to final decision, our process takes around 2 weeks. We make a conscious effort to not keep people in the dark.

A quick decision path means less people to complicate the process. From HR to department leaders, this short path results in fast answers and clear decisions.

Feedback always provided

We appreciate the time, effort and respect every candidate gives us, so we always give feedback to help you progress, regardless of the decision.

Low percentage of rejected job contracts

Very few of our offers are rejected. Between our long reputation and the engaging projects we can offer, we’re confident we can find the ideal place to help you develop and grow.