We are an independent multi-cloud services company that helps enterprises and SMB companies build new foundations for future growth through successful cloud transformation and breadth of expertise in applying cloud technologies to unlock new possibilities. Today's digital and technological revolution is an important part of our business - we are not only adapting to it, but also taking an active part in creating and supporting companies in overcoming the associated challenges.
Our goal is to see the client from their perspective, build relationships based on mutual benefit, and contribute to the efficiency and optimization of clients' businesses.
We are 40+ people, with high seniority, and we specialize in solutions that help our clients in digital transformation. Our company focuses on long-term relationships and offers the opportunity to actively influence the development of the organization. We create an inspiring atmosphere based on transparency and cooperation.
We are on a mission to build Big Data platforms and Serverless applications that host a lot of data and run various analytical workloads. We are looking for talented AI Solution Engineer, who want to embark on this mission with us.
Duties and Responsibilities:
- Working in an agile team delivering LLM based projects.
- Develop, integrate, and optimize cloud-based GenAI applications.
- Build scalable AI solutions using Python, and advanced AI/ML frameworks like LangChain, LangGraph, LlamaIndex, Agno, Pydantic AI.
- Implement advanced architecture patterns — RAG, Multi-Agentic Flows, MCP, Functional Calling.
- Apply prompt engineering, context engineering, and design effective embedding/chunking strategies.
- Work with vector databases and enable real-time data integration for intelligent applications.
- Evaluate and optimize LLM models performance for accuracy, efficiency, and scalability.
Experience, Knowledge and Skills:
- Very good knowledge of Python and Git, more than 5 years of experience in professional Python development
- Excellent programming skills
- 1+ year of experience in delivering applications embedding AI/LLM capabilities
- Familiarity with RAG architectures, Agent-based AI, and data pipelines.
- Experience in prompt/context engineering and vector-based retrieval systems.
- Deep understanding of LLM evaluation & optimization techniques.
- Ability to work as part of the agile team with attitude to help others and learn from them
- Being proactive and having critical-thinking skills
- Native in Polish and fluent in English
It would be nice if you have:
- DevOps skills (Containerization, Infrastructure as a Code, CI/CD pipelines)
Perks & benefits:
- Full-remote work
- Flat organizational structure
- Knowledge-sharing sessions
- Team-building meetings
- Employee referral program
What awaits you at Semantive?
We take care of our team at work and after work! Check out the benefits we have for you:
Remote work and flexible working hours
We work remotely and let you customize your working hours. The mandatory point of the day is team meetings, the rest you can schedule according to your individual preferences.
Medical package
The decision is yours, you can choose LUX MED or Medicover. We cover all costs - your health always comes first.
Support in the first days
Your dedicated Buddy will support you from the very first day at Semantive (and even before).
Be a referral hero
A referral program in which people from Semantive and not only, can participate - and gain up to 8.000 PLN in rewards per referral! Check the details.
Solving real challenges
Our clients impact the lives of millions of people. Here, you're guaranteed to work on big projects that have a real impact on the world.
Knowledge is power
We have a personalized training budget for you (3,600 PLN per year), an online library, access to courses with reviews from people who have gone through them, TECHtalks, newsletters, and much more!
A great Team of great People
Team-building meetings, fully funded by us - accommodation, travel, and great food :) We'll make sure you get to know your team and feel comfortable in it.
Meet our Team
.png)
I have been working at Semantive for six months, I started my adventure in IT here and was very warmly welcomed by colleagues. Here I learned all the ins and outs of the profession and have the opportunity to gain skills in programming and working in a Cloud environment. We have a great atmosphere in the team and I am never left alone with a problem.
Konrad
Junior Software Engineer
What I like most about Semantive is working in international teams, which allows us to develop our communication skills in English and meet very interesting people with great experience.
We run interesting projects for one of the largest companies in the world. I have access to state-of-the-art tools and the cloud. I appreciate the opportunities to broaden my horizons in various directions, though for me personally Big Data, and Data Science
Sylwester
Senior Software Engineer/DevOps
About our recruitment process
Aleksandra
Recruitment Team Lead
01
Introduction
If your profile meets the requirements for one of our positions, we will invite you to a 30-minute phone call or video meeting – the choice is yours!
02
Skills verification
The next step is to connect with our expert who will assess your skills and determine if you possess the necessary competencies. In this part, you can expect a short knowledge test or a case study with practical questions. Clear and concise code is highly important to us, which is why this stage of the recruitment process is crucial.
03
Response within 7 days
We understand that your time is valuable, so we make every effort to provide you with a decision within 7 days. If, in this instance, your skills don't align with the candidate profile we're seeking, we will offer you comprehensive feedback on the matter.
Do you have any questions?
Is English language required? What will be my role when I join the team? What technologies and tools will I be working with? You will find answers to these and other questions here.
