Remote LLM Engineer: Fine-Tuning & RAG Expert

BairesDev; Colombia; Remote; COP 381,934,000 - 509,246,000; Full time

Benefits offered by this job

Remote work

USD compensation

Hardware provided

Flexible hours

Paid parental leave

Vacation and holidays

Multicultural environment

Mentorship & growth

Job summary

BairesDev®, a leader in technology solutions for over 15 years, is seeking an LLM Engineer to design and deploy production-grade AI powered by large language models. You will ground outputs with retrieval-augmented generation (RAG) and build end-to-end pipelines for fine-tuning and deployment.

You will collaborate across teams, implement LangChain-based architectures, optimize prompts, and ensure scalability, reliability, and cost-efficiency while working 100% remotely with a global Top 1%

Qualifications

• 4+ years of experience in Software Engineering, AI/ML, or Data Science.
• Experience building and deploying applications powered by Large Language Models (LLMs).
• Proficiency with LangChain or similar frameworks and RAG approaches.
• Strong ability to design evaluation frameworks for model performance and accuracy.

Responsibilities

• Design and implement robust LLM architectures grounded in external knowledge bases.
• Develop and manage the full lifecycle of LLM fine-tuning pipelines.
• Optimize prompts, evaluation frameworks, and context management for production use.
• Build and deploy production-grade AI agents using LangChain or equivalent tools.
• Collaborate with cross-functional teams to integrate generative AI features into product ecosystems.
• Ensure model reliability and cost-efficiency through monitoring and inference optimization.

Skills

Software Engineering

AI/ML

Data Science

Advanced English

Tools

LangChain

Job description

BairesDev®, a leader in technology solutions for over 15 years, is seeking an LLM Engineer to design and deploy production-grade AI powered by large language models. You will ground outputs with retrieval-augmented generation (RAG) and build end-to-end pipelines for fine-tuning and deployment.

You will collaborate across teams, implement LangChain-based architectures, optimize prompts, and ensure scalability, reliability, and cost-efficiency while working 100% remotely with a global Top 1%