Designing and implementing end-to-end LLM-enabled applications from backend architecture to user-facing components, ensuring scalability and maintainability.
Integrating commercial and open source LLMs (e.g. OpenAI, Anthropic, Meta Llama etc.) into production applications and workflows, using APIs or fine-tuning.
Working with end-to-end RAG pipelines, including embeddings, vector databases (e.g. PostgreSQL + pgvector, chromaDB, pinecone), robust prompt engineering strategies and guardrails
Designing and implementing evaluation pipelines to benchmark the model performance and safety
Collaborating with cross-functional teams, contributing to the development of AI use cases to address complex business challenges
Working together with the client’s tech and business teams and helping them to pick the right technologies suitable for their needs.
Delivering the client and the team with world-class technical expertise.
Other software development-related tasks like contributing to the overall software architecture and design, building test automation and debugging problems.

Experience working with AI software development technologies (LLMs, backend, frontend, ops, and consulting skills) in a production environment.
Experience in deploying AI applications in cloud environments (Azure, AWS, GCP) with containerization/orchestration (Docker, Kubernetes)
We don’t have a hard limit on years of experience, but we’ve noticed that some of these competencies take several years to accumulate.
Foundational knowledge in DevOps, including Continuous Integration (CI), automated deployment, and test automation.
Know-how on vector databases and databases (e.g., PostgreSQL + pgvector, pgvectorscale, chromaDB, pinecone).
Awareness of data privacy (GDPR), security and ethical considerations when handling sensitive data with AI.
To be comfortable engaging with the client stakeholders when needed.
Fluent verbal & written Finnish and English skills.

The ability to impact how you work. Together with the client, your team chooses the approach, technologies, and methodologies you think will work best in any given situation.
A community with as much support as your heart desires.
A team that’s not only experienced but considerate as well – they all want you to succeed.
A sustainable work-life balance and support for your daily life outside of work. (e.g., free moving day, Reaktor car share, sick child care services, office space to use for your private events, etc.).
An opportunity to grow as a professional. In addition to the day-to-day work, we offer internal training courses, community events, and 15-minute coffee breaks to discuss hot topics in tech and design.
A possibility to take part in more extended academy-like studies like Cloud Academy.
300+ hobby clubs, from winter swimming and running to knitting and archery, that bring people together outside of (and sometimes inside) office hours. Many of these are supported by Reaktor.

AI Developer – LLM Applications

Key skills