Prague, Czech Republic
Business overview:
Galytix (GX) is delivering on the promise of AI.
GX has built specialised knowledge AI assistants for the banking and insurance industry. Our assistants are fed by sector-specific data and knowledge and easily adaptable through ontology layers to reflect institution-specific rules.
GX AI assistants are deployed and serving global financial institutions. Our assistants are designed to empower individual Investors, Credit and Claims professionals. Proven, reliable and trusted, our assistants are delivering 10x improvements by supporting professionals in their day- to-day tasks.
If you come with entrepreneurial spirit, desire to learn and passion towards achieving a common goal, we will give you the right resources and create environment in which you can maximise your potential.
You will ship AI products that matter today — semantic ontology-driven assistants used daily by global banks and insurers.
You will own the full LLM development lifecycle from data prep, pipeline architecture, templating, prompt design, model selection, evaluation and fine-tuning, deployment, rollout and monitoring.
You will work with a modern technology stack (language models, traditional ML models, vector databases, NoSQL databases, data lakes, distributed computation frameworks, cloud technologies, application monitoring and observability instrumentation frameworks, etc.) and with best practice software development life-cycle (Kubernetes, microservices, CI/CD, GITOps, MLOps)
You will directly collaborate with company’s leaders and with senior, like-minded, highly motivated, polymath peers. You will be making impactful decisions and having autonomy to shape architecture and engineering standards. You will have opportunity to get involved in adjacent areas such as cloud architecture, MLOps, GitOps and application security.
Detailed role description:
The AI Engineer will bring the rigour of traditional product engineering - testing, reviews, CI/CD, clean architecture, but apply it to Python centric ML and LLM services and bring the same obsession with readable code, SOLID design and reliable releases.
- Expose models behind REST/GraphQL endpoints with FastAPI; ship microservices in Kubernetes; instrument for tracing, canary and A/B rollout.
- Design retrieval augmented generation (RAG) and multi tool agent workflows using LangChain/LlamaIndex style frameworks; manage vector stores (e.g. Qdrant, LanceDB); build prompt libraries and evaluation harnesses; schedule background tasks with Airflow or Ray when scale demands.
- Apply OO & functional patterns, SOLID, typing, pytest, tox; enforce code reviews and CI in Azure DevOps or GitHub Actions.
- Pair program with C# or Angular peers; expose clear contracts; participate in sprint rituals and design docs.
Desired skills:
Why you don’t want to miss this career opportunity:
- Be part of groundbreaking AI projects: Work on the world’s first personalised AI assistants for Financial Institutions, leveraging the latest advancements in Large Language Models (LLMs) to deliver unique data insights.
- Stay at the forefront of Software Engineering and AI / Data: Join a team dedicated to staying on the leading edge of technology, providing you the opportunity to continuously learn and apply new skills in AI-driven data solutions.
- You will work closely with senior leaders who have individually served a number of CEOs in Fortune 100 companies globally.
Interested in learning more about what we’re building? Don’t hesitate to apply – we look forward to connecting with you!
