Senior AI engineer role at LATAM Airlines designing, building, and deploying production Generative AI applications (LLMs, AI agents, RAG) on AWS. Day to day involves Python/FastAPI backend services, AI platform integrations (Azure OpenAI, Bedrock, Vertex AI), prompt engineering, and Terraform/Docker-based cloud infrastructure, with mentoring and technical leadership.
Role Overview
We are looking for a Senior AI Engineer who can design, build, and deploy production-ready AI solutions using modern Large Language Models (LLMs), AI agents, and cloud-native architectures. The ideal candidate combines strong software engineering fundamentals with hands-on experience building scalable AI applications, integrating foundation models, and delivering business value through Generative AI.
Key Responsibilities
- Design, develop, and maintain AI-powered applications using Large Language Models
(LLMs) and Generative AI technologies
- Build AI agents and Retrieval-Augmented Generation (RAG) solutions to enable intelligent workflows and knowledge-based applications.
- Integrate leading AI platforms such as Azure OpenAI, Amazon Bedrock, Google Vertex AI, or similar services.
- Develop scalable backend services and APIs using Python and modern frameworks such as FastAPI.
- Collaborate with frontend engineers to deliver end-to-end AI applications using technologies such as React.
- Design prompt engineering strategies to improve model accuracy, reliability, and user experience.
- Implement intelligent routing, semantic search, vector databases, and knowledge retrieval solutions.
- Deploy and manage cloud-native AI applications using AWS and Infrastructure as Code tools such as Terraform.
- Build and maintain CI/CD pipelines, containerized applications, and cloud infrastructure using Docker and DevOps best practices.
- Evaluate emerging AI frameworks, tools, and models to continuously improve platform capabilities.
- Collaborate with Product Managers, Architects, and Engineering teams to translate business requirements into scalable AI solutions.
- Mentor engineers and contribute to technical leadership, architecture discussions, and engineering best practices.
Required Qualifications
- 10+ years of experience in Software Engineering with recent hands-on experience building Generative AI solutions.
- Strong experience with Python and REST API development.
- Experience developing production AI applications using Large Language Models (LLMs).
- Hands-on experience with AI agent frameworks such as LangChain, CrewAI, or similar technologies.
- Experience implementing Retrieval-Augmented Generation (RAG) architectures.
- Experience integrating AI platforms such as Azure OpenAI, Amazon Bedrock, Google Vertex AI, or equivalent services.
- Strong understanding of prompt engineering techniques and AI application design patterns.
- Experience developing scalable cloud applications on AWS.
- Experience with Docker, Terraform, CI/CD pipelines, and Infrastructure as Code.
- Experience with SQL and NoSQL databases.
- Familiarity with React or modern frontend technologies.
- Experience working within Agile software development environments.
- Strong understanding of software architecture, API design, and distributed systems.
- Experience working in cross-functional and multicultural teams.
Working Style
- Strong communication skills: able to clearly explain complex AI concepts to both technical and non-technical audiences.
- Proactive mindset: identifies opportunities for innovation and continuously explores new AI technologies.
- Ownership and accountability: takes responsibility for delivering reliable, scalable, and maintainable AI solutions.
- Collaborative attitude: works effectively across product, engineering, architecture, and business teams.
- Adaptability: thrives in a rapidly evolving AI landscape and embraces continuous learning.
- Attention to detail: prioritizes quality, security, observability, and responsible AI practices.
- Customer-oriented thinking: focuses on solving real business problems through practical AI solutions.
- Continuous learner: stays current with advancements in LLMs, AI frameworks, cloud services, and software engineering best practices