(1609) Senior AI Engineer (Full Stack)

Role overview

Build production AI applications that turn early business ideas into useful tools for teams across a global organization. The role combines full-stack software engineering, LLM application development, and enterprise data integration, with responsibility for connecting AI agents to business systems and supporting their safe, reliable adoption.

Responsibilities - Translate loosely defined business problems into scalable AI features, applications, and standalone tools. - Design persistent AI memory and vector-search capabilities while addressing privacy, retention, and deletion requirements. - Build data pipelines and entity-resolution logic to bring information together across systems such as CRM, ERP, quoting, and marketing platforms. - Work with business teams to identify valuable use cases, prioritize solutions, and support implementation and user adoption. - Create ongoing evaluation and safety processes that check for hallucinations, prompt injection, data leakage, and regressions. - Improve model cost and response time through techniques such as caching, model routing, and inference optimization; share deployment feedback with engineering teams.

Requirements - Five or more years of software engineering experience, with strong backend, distributed-systems, asynchronous programming, API, microservices, and database skills. - At least two years delivering production AI or LLM applications, including LLM APIs, retrieval-augmented generation (RAG), or agent workflows. - Three or more years building data pipelines and integrating enterprise systems, with skills in transformation, entity resolution, schemas, and data quality. - Three or more years of Python or equivalent backend development experience. - Hands-on cloud deployment experience and experience working directly with business and engineering stakeholders to deliver production solutions. - Practical experience with vector databases and AI memory, orchestration frameworks, model evaluation and safety, or performance optimization, as applicable to the role’s stated experience ranges.

Nice to have

Experience with tools such as Pinecone or pgvector, LangChain or LlamaIndex, and cloud platforms including AWS, Azure, or Google Cloud is relevant. The listing describes a fully remote arrangement for workers in Latin America, a USD salary, paid leave and holidays, sick leave, an annual benefits credit, and team activities.