LLM Engineer - Remote Work

Role Overview

You’ll be an LLM Engineer designing and building production-ready AI applications powered by large language models (LLMs). The focus is on fine-tuning and retrieval-augmented generation (RAG), translating business requirements into accurate, scalable, and reliable generative systems.

Responsibilities

• Design and implement RAG architectures that ground LLM responses in external knowledge bases.
• Build and manage LLM fine-tuning pipelines across the full lifecycle to match domain needs.
• Optimize performance using advanced prompt engineering, evaluation frameworks, and context management.
• Develop and deploy production-grade AI agents using orchestration frameworks such as LangChain.
• Collaborate cross-functionally to integrate generative AI features into existing products.
• Ensure reliability and cost efficiency via monitoring, validation layers, and inference optimization.

Requirements

• 4+ years of experience in Software Engineering, AI/ML, or Data Science.
• Proven experience building and deploying LLM-powered applications.
• Hands-on expertise in fine-tuning, RAG, and prompt engineering.
• Proficiency with LLM frameworks, especially LangChain (or similar).
• Ability to design evaluation frameworks for accuracy and model performance.
• Advanced English proficiency.

Nice to Have

• Not explicitly stated, but strong production experience with monitoring/validation and inference optimization is implied by the responsibilities.

Work Setup

• 100% remote (work from anywhere), flexible hours, and company-provided hardware/software setup.