Are you passionate about building the future of AI-driven systems? We're looking for a Senior Generative AI Developer to join a forward-thinking, AI-first team delivering innovative GenAI capabilities for a global financial institution. You'll help architect, build, and scale secure and low-latency systems that enable cutting-edge applications using LLMs, RAG pipelines, and modern AI toolchains.
🧠 What You’ll Be Working On:
-
Designing and implementing backend systems to support Generative AI workflows and services.
-
Developing microservices and APIs that integrate with LLMs, vector databases, and orchestration frameworks like LangChain or LangGraph.
-
Building scalable infrastructure for deploying and serving LLMs and AI pipelines in production.
-
Creating and maintaining data pipelines to support GenAI use cases — including prompt processing and model feedback loops.
-
Collaborating with AI/ML engineers to develop plug-and-play components (e.g., Intent Resolver, Tool Agent, LLM Gateway) in agentic workflows.
-
Participating in architecture reviews to ensure performance, latency, and modularity of GenAI systems.
-
Debugging and optimizing prompt execution, model inference paths, and external API integration.
-
Writing documentation on service design, deployment procedures, and best practices.
✅ Must-Have Skills:
-
5+ years of total IT experience, with at least 1+ year hands-on with GenAI/LLMs (prompt engineering, embeddings, fine-tuning, or RAG).
-
Strong backend engineering skills in Python, Java, or Scala - Python preferred.
-
Proficiency with REST APIs, Kafka, and cloud platforms (AWS or Azure).
-
Experience with scalable systems architecture, microservices, and secure backend development.
💡 Desired Skills:
-
Familiarity with LangChain, LangGraph, Copilot, or vector databases.
-
Hands-on experience with Docker, Kubernetes, CI/CD, and Git.
-
Exposure to prompt engineering, AI agent orchestration, or AI-first development environments is a strong plus.
🔧 Tech Stack Highlights:
-
Languages: Python, Java, Scala
-
GenAI Tools: LLMs, LangChain, LangGraph, RAG pipelines
-
Infrastructure: AWS, Azure, Docker, Kubernetes, Kafka
-
DevOps: Git, CI/CD
-
Architecture: Microservices, REST APIs, Secure AI Systems
🏢 Work Model:
-
Hybrid: 1 day/week in the Kraków office, 4 days remote
-
EU-based candidates only
-
Long-term engagement in an enterprise AI transformation program
Join an AI-first engineering team working on real-world LLM and RAG applications in a secure and scalable enterprise setting. You’ll gain hands-on exposure to some of the most advanced GenAI technologies in production today.
Apply now and help shape the future of enterprise AI!