Industry: Public transport

Working model: 100% remote (occasional travel to Denmark possible)

Workload: Full-time

Project length: 6 months (+ extension) 

Type of assignment:  B2B up to 200 PLN net/hour

Start: 1 month notice

BYOD: yes

The Senior AI Engineer role is focused on developing and enhancing large language model (LLM) infrastructure within the GenAI team. This position is crucial for supporting and evolving internal AI applications used across the organization, ensuring high performance and reliability in production environments.

Responsibilities

• Further develop and extend the Litellm-based LLM gateway for routing and model management.

• Design and maintain REST APIs with FastAPI, ensuring scalability and reliability.

• Build agent architectures using frameworks like LangGraph for multi-agent functionality.

• Implement observability tools for monitoring performance and reliability.

• Optimize the deployment of the LLM gateway on Kubernetes.

• Integrate Azure AI services with internal LLMs.

• Collaborate with AI and ML engineers to improve AI components.

• Participate in technical design sessions and code reviews.

Key Requirements

• Strong background in Python software engineering.

• Experience in high-performance programming in production.

• Expertise in developing REST APIs, particularly using FastAPI.

• Hands-on LLM integration and agent frameworks experience.

• Proven track record in delivering production-grade AI systems.

• Strong Docker and container deployment knowledge.

• Kubernetes experience in real environments.

• Familiarity with Azure AI services.

• Experience with observability tools like Grafana.

• Experience with Model Context Protocol (MCP).

Nice to Have

• Understanding of RAG pipeline strategies.

• Knowledge of retrieval concepts.

• Experience with RAG evaluation frameworks.

• Basics of prompt engineering and LLM evaluation.

• Experience with Databricks.

• Exposure to ML workflows and experimentation.