Software Engineer - LLM | Remote

Crossing Hurdles; United States; On-site; USD 130,000 - 190,000; Full time

Job summary

Crossing Hurdles is seeking an experienced AI/ML engineer to design, build, and deploy scalable AI systems for enterprise applications in the United States. You will work on LLMs, RAG pipelines, and agent‑based architectures to deliver robust solutions.

Responsibilities include developing Python APIs, building data pipelines, and integrating cloud services with secure coding, CI/CD workflows, and production deployments.

Qualifications

• Experience with LLMs, RAG, and AI architectures.
• Proficiency in Python, API development, and secure coding.
• Experience with cloud platforms like AWS.
• Strong data pipelines and ETL knowledge.
• Experience with CI/CD and deployment workflows.
• Excellent written and verbal communication skills.

Responsibilities

• Design, build, and deploy advanced AI/ML solutions for scalable and secure applications.
• Develop and optimize systems leveraging LLMs, RAG pipelines, and agent-based architectures.
• Build and maintain APIs, integrations, and data pipelines using Python and cloud services.
• Collaborate with cross-functional teams to architect AI-driven platforms and workflows.
• Implement prompt engineering strategies and integrate tools for intelligent AI systems.
• Ensure robust deployment practices using CI/CD pipelines and cloud infrastructure.
• Communicate technical concepts effectively to both technical and non-technical stakeholders.

Skills

Python

API development

Secure coding

Large language models

RAG systems

AI architectures

Data pipelines

ETL processes

CI/CD pipelines

Cloud platforms (AWS)

Prompt engineering

Job description

• Design, build, and deploy advanced AI/ML solutions for scalable and secure applications.
• Develop and optimize systems leveraging LLMs, RAG pipelines, and agent-based architectures.
• Build and maintain APIs, integrations, and data pipelines using Python and cloud services.
• Collaborate with cross-functional teams to architect AI-driven platforms and workflows.
• Implement prompt engineering strategies and integrate tools for intelligent AI systems.
• Ensure robust deployment practices using CI/CD pipelines and cloud infrastructure.
• Communicate technical concepts effectively to both technical and non-technical stakeholders.

Requirements

• Strong experience with large language models, RAG systems, and AI architectures.
• Strong proficiency in Python, API development, and secure coding practices.
• Experience working with cloud platforms such as AWS or similar environments.
• Strong understanding of data pipelines, ETL processes, and system design.
• Experience with prompt engineering and AI system optimization.
• Familiarity with CI/CD pipelines and production deployment workflows.
• Excellent written and verbal communication skills.