Sr. AI Engineer

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

Benefits offered by this job

Flexible hours

25 days paid time off

Equipment provided

English classes

Job summary

Devlane seeks an experienced backend engineer to design and deploy generative AI capabilities in production. You will connect LLMs to application workflows, build retrieval-augmented and multi-step AI processes, and work with AI, DevOps, and software teams to deliver scalable services.

The role requires 7+ years in software engineering, strong Python, and hands-on experience with Docker/Kubernetes, CI/CD, and cloud platforms. Advanced English is a must.

Qualifications

• 7+ years of software engineering experience
• Strong Python and backend services in production
• Deep practical knowledge of generative AI including LLM APIs, RAG, multi-step workflows, and prompt engineering
• Experience integrating foundation models and optimizing embeddings
• Familiarity with AWS/Azure/GCP
• Hands-on Docker, Kubernetes, Git, and CI/CD
• Advanced English proficiency

Responsibilities

• Build and scale production backend services in Python.
• Integrate language model APIs and foundation models into applications.
• Develop retrieval-augmented generation pipelines and multi-step AI workflows.
• Improve model responses through prompt design, debugging, and performance evaluation.
• Assess and address output accuracy, bias, compliance, and performance concerns.
• Collaborate with AI, DevOps, and software engineering colleagues on production readiness.

Skills

Python backend

LLM/prompt engineering

Cloud platforms

CI/CD

English proficiency

Tools

Docker

Kubernetes

Git

CI/CD tooling

LlamaIndex

Job description

Role overview

Design, build, and bring generative AI capabilities into production, with a focus on backend systems and applied AI engineering. You will connect large language models to application workflows, develop retrieval-augmented and multi-step processes, and work with engineering and operations teams to deliver reliable, scalable services.

Responsibilities

• Build and scale production backend services in Python.
• Integrate language model APIs and foundation models into applications.
• Develop retrieval-augmented generation pipelines and multi-step AI workflows.
• Improve model responses through prompt design, debugging, and performance evaluation.
• Assess and address output accuracy, bias, compliance, and performance concerns.
• Collaborate with AI, DevOps, and software engineering colleagues on production readiness.

Requirements

• At least seven years of software engineering experience and a solid grasp of architecture and engineering practices.
• Strong Python skills and experience operating backend services in production.
• Deep practical knowledge of generative AI, including LLM APIs, RAG, multi-step workflows, and prompt engineering.
• Experience integrating foundation models, using LlamaIndex or similar frameworks, and optimizing embeddings.
• Familiarity with at least one major cloud platform: AWS, Azure, or GCP.
• Hands-on experience with Docker, Kubernetes, Git, and CI/CD.
• Advanced English proficiency.

Benefits and work setup

This is a fully remote role for candidates based in Latin America. The package includes USD compensation, 25 paid days off annually, flexible hours within an eight-hour workday, and supplied computer equipment. Learning support includes English classes, a virtual library, and online courses; contribution bonuses are also offered.