GenAI Engineer: Build Scalable LLM Apps in Cloud

Capco; Poland; On-site; PLN 180,000 - 240,000; Full time

Job summary

Capco, a global technology and management consulting firm, is seeking a GenAI Developer in Poland to design, build, and deploy scalable AI-powered applications using large language models. You will work in cross-functional agile teams to deliver production-ready solutions integrated into enterprise environments.

The role emphasizes strong backend and cloud expertise with modern AI capabilities, including prompt engineering and RAG architectures, in a client-facing consulting setting.

Qualifications

• Must have hands-on Python development experience.
• Experience with Google Cloud Platform services (Vertex AI, BigQuery).
• Practical work with LLM APIs (OpenAI, Vertex AI).
• Understanding of prompt engineering and RAG architectures.
• Experience building REST APIs and microservices.
• Strong communication for consulting environments.

Responsibilities

• Design, build, and deploy AI applications leveraging LLMs.
• Develop scalable solutions on GCP (Vertex AI, BigQuery, Cloud Run/Functions).
• Integrate LLM APIs into enterprise systems.
• Design and implement RAG architectures.
• Apply prompt engineering to optimize model performance.
• Build and maintain REST APIs and microservices.
• Collaborate with cross-functional teams in agile settings.
• Deliver production-grade solutions to clients.

Skills

Python

GCP Vertex AI

BigQuery

REST APIs

Microservices

LLM APIs

Prompt engineering

RAG architectures

Tools

Vertex AI

BigQuery

Cloud Run/Functions

Job description

Capco, a global technology and management consulting firm, is seeking a GenAI Developer in Poland to design, build, and deploy scalable AI-powered applications using large language models. You will work in cross-functional agile teams to deliver production-ready solutions integrated into enterprise environments.

The role emphasizes strong backend and cloud expertise with modern AI capabilities, including prompt engineering and RAG architectures, in a client-facing consulting setting.