AI LLM Engineer in EMEA

Workster Jobs; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Workster Jobs is seeking an AI LLM Engineer to build and improve AI-powered products. You will design and integrate LLM features, build backend components and APIs, develop prompts, explore RAG and embeddings, and evaluate model outputs.

You will work with product and engineering colleagues in a remote, international environment across the LLM development lifecycle. You will collaborate with stakeholders to define requirements, document decisions, and drive reliable AI solutions while

Qualifications

• Experience building applications or services that use large language models.
• Strong programming skills in Python or another relevant language.
• Understanding of LLM APIs, prompt design and the strengths and limitations of generative AI models.
• Experience with backend development, APIs and integrating external services.
• Familiarity with data handling, privacy and security considerations when working with AI systems.

Responsibilities

• Design, develop and integrate LLM-powered features and services.
• Build and maintain reliable backend components and APIs for AI applications.
• Develop and refine prompts, workflows and model configurations to improve response quality.
• Explore techniques such as retrieval-augmented generation (RAG), embeddings and tool use where appropriate.
• Evaluate model outputs for quality, accuracy, consistency and relevance using appropriate tests and metrics.
• Monitor AI features in production and investigate performance or reliability issues.
• Collaborate with product, engineering and other stakeholders to define requirements and deliver solutions.
• Contribute to decisions about model selection, integration approaches and system architecture.
• Apply responsible AI practices, considering privacy, security, safety and potential model limitations.
• Document technical decisions, workflows and evaluation results.
• Keep up to date with developments in LLMs and related AI technologies, identifying opportunities to improve products.

Skills

Python

LLM APIs

Backend development

Data handling & privacy

Remote collaboration

Tools

APIs

Vector databases

Embeddings

CI/CD

Containers

Job description

Описание: Our client is looking for an AI LLM Engineer to help build and improve AI-powered products. In this role, you will develop and integrate large language model (LLM) solutions, turning product and user needs into reliable, high-quality features. You will work with engineering and product colleagues in a remote, international environment, contributing across the LLM development lifecycle—from experimentation and evaluation to deployment and ongoing improvement.

Задачи:

• Design, develop and integrate LLM-powered features and services
• Build and maintain reliable backend components and APIs for AI applications
• Develop and refine prompts, workflows and model configurations to improve response quality
• Explore techniques such as retrieval-augmented generation (RAG), embeddings and tool use where appropriate
• Evaluate model outputs for quality, accuracy, consistency and relevance using appropriate tests and metrics
• Monitor AI features in production and investigate performance or reliability issues
• Collaborate with product, engineering and other stakeholders to define requirements and deliver solutions
• Contribute to decisions about model selection, integration approaches and system architecture
• Apply responsible AI practices, considering privacy, security, safety and potential model limitations
• Document technical decisions, workflows and evaluation results
• Keep up to date with developments in LLMs and related AI technologies, identifying opportunities to improve products

Требования:

• Professional experience in software engineering, machine learning or a related technical role
• Experience building applications or services that use large language models
• Strong programming skills in Python or another relevant language
• Understanding of LLM APIs, prompt design and the strengths and limitations of generative AI models
• Experience with backend development, APIs and integrating external services
• Familiarity with evaluation methods for AI systems, including testing model outputs and tracking quality
• Understanding of data handling, privacy and security considerations when working with AI systems
• Experience with RAG, vector databases, embeddings or AI orchestration frameworks is an advantage
• Familiarity with cloud platforms, containers, CI/CD or production monitoring is an advantage
• Strong analytical and problem-solving skills, with attention to reliability and maintainability
• Clear communication skills and the ability to collaborate effectively in a remote team
• Comfortable working independently, managing priorities and adapting to a fast-changing technical landscape
• Ability to work remotely within the EMEA region

The Offer

Remote opportunity for candidates based in the EMEA region Opportunity to build and improve products powered by large language models Collaborative work with colleagues across product and engineering Scope to contribute to technical decisions and the development of AI solutions