Senior AI Engineer — Remote/Hybrid, LLMs & Cloud

Billennium; Poland; Hybrid; PLN 180,000 - 240,000; Full time

Benefits offered by this job

Udemy for Business

Private medical care

Multisport card

Veterinary package

Language lessons

Shopping vouchers

Remote/hybrid work options

Career growth opportunities

Team-building events

Annual Mazury company event

Welcome pack

Job summary

Billennium, a global technology company, is seeking an experienced Senior Developer with strong Python, cloud-native development and AI/LLM expertise. You will contribute to building production-grade intelligent solutions used by enterprise clients worldwide.

In this role you will design and implement scalable FastAPI services, develop end-to-end LLM-powered features, and optimize AI workflows, latency and costs while collaborating with a diverse, international team.

Qualifications

• Solid understanding of software architecture, design patterns and API development.
• Hands-on experience with LLM APIs and AI-driven applications.
• Good understanding of RAG, prompt engineering and LLM evaluation.
• Experience with LangGraph or similar agentic AI frameworks.
• Experience with FastAPI or similar Python frameworks.
• Strong knowledge of Azure, Docker and Kubernetes.
• Familiarity with CI/CD and IaC tools like Terraform, Bicep or ARM.
• Experience with monitoring/observability tools (App Insights, Prometheus, Grafana).
• Proven scalability, performance optimization and production troubleshooting.
• Experience with code reviews, mentoring and establishing engineering standards.
• Fluent English and strong communication skills.

Responsibilities

• Build LLM-powered features end to end.
• Design and implement agentic workflows, RAG and tool calling using LangGraph.
• Develop scalable FastAPI services with streaming, persistence and automated tests.
• Build evaluation datasets, regression suites and LLM-as-a-judge solutions to measure and improve answer quality.
• Design effective retrieval strategies and orchestrate multi-step research workflows.
• Investigate AI-related issues and identify root causes (retrieval, prompting, model).
• Instrument and debug production AI workflows using Langfuse and tracing.
• Optimize latency, token usage and AI costs, including model routing via AI gateway.
• Build and optimize scalable backend systems in Azure.

Skills

Software architecture

API development

LLM APIs

RAG

Prompt engineering

LangGraph

FastAPI

Python

Azure

Docker

Kubernetes

CI/CD

Infrastructure as Code

Observability tools

English communication

Tools

Azure

Docker

Kubernetes

Terraform

Bicep

ARM

Application Insights

Prometheus

Grafana

Job description

Billennium, a global technology company, is seeking an experienced Senior Developer with strong Python, cloud-native development and AI/LLM expertise. You will contribute to building production-grade intelligent solutions used by enterprise clients worldwide.

In this role you will design and implement scalable FastAPI services, develop end-to-end LLM-powered features, and optimize AI workflows, latency and costs while collaborating with a diverse, international team.