Full-Stack AI Engineer
Aviso de fuente externaen Elevate
We are looking for a Full-Stack AI Engineer who combines strong software engineering skills with hands-on experience building and deploying production-grade AI products. You should be pas...
Salario
No especificado
Ubicación
Heredia, Costa Rica
Tipo de empleo
Tiempo completo
Modalidad
No especificado
Full-Stack AI Engineer
Heredia, Costa Rica
Descripción del empleo
We are looking for a Full-Stack AI Engineer who combines strong software engineering skills with hands-on experience building and deploying production-grade AI products. You should be passionate about AI and have a proven track record of turning LLM capabilities into real-world applications.
What You’ll DoDesign, build, and deploy end-to-end AI-powered products from concept to production.Develop full-stack solutions using Java, Python, and TypeScript/JavaScript.Build and integrate LLM-powered applications, including RAG pipelines, AI agents, and tool-calling workflows.Work with MCP (Model Context Protocol) and other modern AI integration patterns.Design and implement LLM evaluation frameworks (evals) to measure and continuously improve AI performance.Build scalable, reliable, and maintainable backend and frontend services.Collaborate with product and engineering teams to identify opportunities where AI can deliver meaningful business value.Stay up to date with the rapidly evolving LLM and generative AI ecosystem and apply relevant technologies to production use cases.
What We’re Looking For3+ years of hands-on experience shipping LLM/AI products into production.Strong full-stack development experience with:JavaPythonTypeScript / JavaScriptProven experience building and deploying AI products multiple times, not just prototypes or POCs.Strong hands-on experience with:RAG (Retrieval-Augmented Generation)AI agents / agentic workflowsMCP and tool/function callingLLM evaluations and testingStrong understanding of modern LLM architectures, APIs, and AI application patterns.Experience taking AI solutions from prototype → production → ongoing improvement.Strong problem-solving skills and an ability to work independently in a fast-moving environment.Genuine passion for AI and curiosity about emerging technologies.
Nice to HaveExperience with multiple LLM providers and models.Experience with vector databases and embeddings.Familiarity with AI observability, guardrails, and production monitoring.Experience with cloud platforms and modern DevOps practices.Contributions to AI/ML projects, open-source projects, or a strong personal AI portfolio.
Why Join?You’ll have the opportunity to work on real-world AI products, using the latest LLM technologies and agentic architectures. This is a hands-on engineering role for someone who enjoys building, experimenting, and shipping AI into production.If you have already shipped multiple AI products and are excited about what’s next in AI, we’d love to hear from you.
¿Es tuya esta vacante?
Reclámala gratis y recibe candidatos con video en CazVid.