Full Stack AI Engineer
Enumerate
- Remote · Latin America
- Remote
- Mid Level
- Posted
to join our AI Pod. This is a highly hands-on engineering role focused on building and delivering AI-powered product capabilities.
We are looking for a strong full-stack developer who has practical experience building applications using Large Language Models (LLMs), understands the modern AI application stack, and brings strong data engineering instincts.
The ideal candidate can work across frontend interfaces, backend services, LLM integrations, and enterprise data platforms to turn AI capabilities into reliable, scalable product features.
This is a remote contractor opportunity for candidates located in LATAM who are comfortable working in an English-speaking professional environment.
About Enumerate
Enumerate is hiring a
Responsibilities
End-to-End Feature Development
- Design and implement user-facing features across frontend and backend systems
- Build and evolve APIs and services that integrate data pipelines and product workflows
- Translate product requirements and UX designs into high-quality, maintainable code
- Rapidly prototype and iterate based on user feedback and experimentation results
- Design, build, and deploy AI-powered product features using LLMs and modern AI development frameworks.
- Implement LLM application patterns including prompt engineering, retrieval-augmented generation (RAG), embeddings, vector search, and tool/function calling.
- Build backend services that integrate LLMs with application workflows, APIs, and enterprise data.
- Develop AI-driven workflows and agentic capabilities that can retrieve information, reason over data, and execute actions through application services.
- Implement appropriate safeguards, grounding, evaluation, and human-in-the-loop mechanisms to ensure reliable AI behavior.
- Optimize AI applications for response quality, latency, reliability, and cost.
Data Integration & AI Readiness
- Work with structured and unstructured enterprise data to enable AI-powered features.
- Integrate AI applications with data lakes, databases, APIs, and data services.
- Understand data ingestion, transformation, data modeling, and retrieval patterns that support AI applications.
- Apply strong data quality instincts, including an understanding of data lineage, freshness, consistency, and source-of-truth considerations.
- Collaborate with data engineering teams to make enterprise data accessible, trustworthy, and usable by AI applications.
- Design efficient data access and retrieval patterns for LLM-powered applications, balancing accuracy, performance, and cost.
- Frontend & UX Integration
- Implement intuitive user interfaces
Handle edge cases, fallbacks, and user feedback
- Ensure UI performance, accessibility, and responsiveness.
- Develop backend services that orchestrate business logic, and data access.
- Integrate with internal APIs, data services, and third-party AI platforms.
- Implement secure, scalable request handling, including latency and cost considerations
- Support feature flags, configuration, and experimentation frameworks.
- Quality, Reliability & Observability
- Write automated tests across frontend and backend components.
- Implement logging, monitoring, and basic performance tracking
- Participate in code reviews and adhere to team engineering standards
- Help diagnose and resolve production issues
Requirements
- 4+ years of professional experience building full-stack web applications.
- Strong proficiency in modern frontend frameworks such as React, Vue, or similar.
- Strong backend development experience, preferably with Python, Node.js, Java, or Go.
- Experience designing, building, and integrating REST or GraphQL APIs.
- Demonstrated hands-on experience building LLM-powered applications or AI-enabled product functionality.
- Practical familiarity with the LLM application stack, including prompting, RAG, embeddings, vector databases, and model APIs.
- Experience integrating applications with structured data sources, databases, and data pipelines.
- Working understanding of data lake concepts, data modeling, and data quality considerations.
- Experience with cloud environments, preferably AWS.
