LLM Engineer; Cloud AI Solutions IRC

LLM Engineer (Cloud Based AI Solutions) IRC
291168

Designation:
Consultant

Function:
Engineering

Experience:

5‑10 years

Location:

Poland — Szczecin

Skills:

AWS Bedrock, Azure OpenAI, Data Integrator, Generative AI, Generative AI – LLMs, Generative AI – Tools, Generative AI:
Prompt Engineering, MCP, Retrieval-Augmented Generation (RAG)

The LLM Engineer will join a team focused on building cloud‑based AI solutions that leverage modern language models and advanced orchestration patterns. The role involves creating scalable, production‑ready systems that transform raw or distributed data into meaningful outputs and automated reasoning. The engineer will work closely with project teams, support client engagements, and help shape the department’s AI solution portfolio.

• Strong experience working with large language models, including fine‑tuning, prompt engineering, and integrating LLMs into production systems.
• Hands‑on familiarity with cloud AI platforms such as AWS, Azure, or GCP, including their LLM‑related services, orchestration tools, and deployment environments.
• Understanding of retrieval‑augmented generation (RAG), embedding databases, vector search, and model‑driven reasoning pipelines.
• Ability to design end‑to‑end AI solutions, connecting cloud components with data sources, APIs, and downstream applications.
• Experience implementing model context protocols (MCP) or similar integration patterns for connecting LLMs with external tools and systems.
• Comfortable collaborating with cross‑functional teams, contributing to solution architecture, and supporting offering/pre‑sales activities.

• Build and deploy LLM‑based applications using cloud native services (e.g., AWS Bedrock, Azure OpenAI, managed vector databases, serverless components).
• Design and implement RAG pipelines, including embedding generation, vector storage, retrieval logic, and LLM orchestration.
• Integrate LLMs with enterprise data sources, APIs, and external tools using MCP or equivalent frameworks.
• Develop prompt templates, reasoning flows, and model interaction logic to ensure reliable, structured outputs.
• Monitor and evaluate LLM performance, cost efficiency, latency, and scalability within cloud environments.
• Collaborate with internal teams to design client solutions and contribute technical expertise to proposals and offering processes.

Culture of caring. At Global Logic, we prioritize a culture of caring. Across every region and department, at every level, we consistently put people first. From day one, you’ll experience an inclusive culture of acceptance and belonging, where you’ll have the chance to build meaningful connections with teammates, supportive managers, and compassionate leaders.

Learning and development. We commit to your continuous learning and development. You’ll learn and grow daily in an environment with many opportunities to try new things, sharpen your skills, and advance your career. With tools like the Career Navigator, we offer a range of programs, training curricula, and hands‑on opportunities.

Interesting & meaningful work. We are known for engineering impact for clients worldwide. You’ll work on projects that matter, engaging your curiosity and creative problem‑solving skills to help clients reimagine what’s possible and bring new solutions to market.

Balance and flexibility. We believe in balance and flexibility. With many functional career areas, roles, and work arrangements, you can find ways to balance work and life, integrating your best balance and enjoying the work.

High‑trust organization. We are a high‑trust organization where integrity is key. Your trust is placed in a safe, reliable, and ethical global company. Integrity and trust are cornerstone of our values to employees and clients.