Full-Stack AI Engineer (LLMs, RAG, AI Agents) for 100% Remote LATAM at EROS Technologies Inc. | Torre

Full-Stack AI Engineer (LLMs, RAG, AI Agents) for 100% Remote LATAM

Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Full-time

Legal agreement: Employment

Provide your expected compensation while applying
location_on
Remote (for Colombia residents)
Remote (for Mexico residents)
Remote (for Brazil residents)
Remote (for Argentina residents)
Shared by
Gabriela Enríquez Meléndez
4 days ago

Responsibilities


We’re looking for a Full-Stack AI Engineer who can turn AI ideas into scalable, production-ready applications.What You’ll DoYou’ll work across the full technology stack, building modern applications powered by LLMs, AI Agents, RAG, embeddings, vector databases, and AI APIs.Build scalable full-stack web applicationsDevelop AI-powered features and user experiencesBuild LLM, RAG, and AI Agent solutionsDesign scalable APIs and microservicesImplement embeddings and vector database solutionsDevelop prompt engineering and AI evaluation strategiesIntegrate platforms such as OpenAI, Anthropic, Google, and open-source modelsDeploy applications to AWS, Azure, or GCPBuild CI/CD, testing, monitoring, and observabilityOptimize systems for performance, reliability, security, and costTake AI prototypes from concept → productionWhat We’re Looking For10+ years of professional software engineering experienceStrong Python and/or TypeScript/JavaScriptStrong experience with React / Next.jsBackend experience with Node.js, Python, FastAPI, Django, or similarREST and/or GraphQL API experienceExperience with PostgreSQL, MySQL, MongoDB, Redis, or similar databasesHands-on experience building LLM / Generative AI applicationsExperience with RAG, embeddings, vector databases, and prompt engineeringStrong knowledge of Git, Docker, CI/CD, and cloud deploymentSolid understanding of architecture, scalability, security, and testing⭐ Nice to HaveAI Agents / Multi-Agent SystemsLangChain / LlamaIndexPinecone / Weaviate / Qdrant / pgvectorAI evaluation, observability, safety & guardrailsFine-tuning or adapting open-source modelsAWS / Azure / GCP AI/ML servicesKubernetes & Infrastructure as CodeTaking AI prototypes into reliable production systemsOpen-source contributions or a strong AI/full-stack portfolio🛠️ Tech StackFrontend: React, Next.js, TypeScript, JavaScriptBackend: Python, FastAPI, Node.jsAI/ML: LLMs, RAG, AI Agents, Embeddings, Prompt EngineeringDatabases: PostgreSQL, Redis, MongoDB, Vector DBsCloud: AWS / Azure / GCPDevOps: Docker, Kubernetes, GitHub Actions / CI/CDAI Frameworks: OpenAI, Anthropic, LangChain, LlamaIndex