Remote AI Engineer: LLM & RAG Pipeline Architect

Neubrain; United States; Remote; USD 90,000 - 120,000; Full time

Job summary

Neubrain is seeking an AI Engineer for a 100% remote role in the US. You will own LLM-powered feature development, RAG architecture, and deployment. Expect mentorship, rapid growth, and a strong emphasis on building real-world AI products.

Ideal candidates have Python, ML basics, and hands-on work with LangChain/LlamaIndex. You will collaborate with product and engineering teams to ship production-grade AI solutions.

Qualifications

• Bachelor's degree or equivalent in a technical field.
• 0–2 years of AI/ML software engineering experience.
• Proficient in Python and asynchronous development.
• Familiar with LLMs, REST APIs, and modern orchestration tools.

Responsibilities

• Build and deploy LLM-powered features in production.
• Design and optimize RAG pipelines and prompts.
• Fine-tune models balancing quality, latency, and cost.
• Collaborate with product, software, and data science teams.
• Produce thorough technical documentation and runbooks.

Skills

Python

Async programming

PyTorch

LLMs / NLP

REST APIs

LangChain / LlamaIndex

Problem solving

Communication skills

Education

Bachelor's degree in CS/AI/DS

Tools

LangChain

LlamaIndex

TensorFlow

CI/CD for ML

Job description

Neubrain is seeking an AI Engineer for a 100% remote role in the US. You will own LLM-powered feature development, RAG architecture, and deployment. Expect mentorship, rapid growth, and a strong emphasis on building real-world AI products.

Ideal candidates have Python, ML basics, and hands-on work with LangChain/LlamaIndex. You will collaborate with product and engineering teams to ship production-grade AI solutions.