Senior AI Developer (Full Stack) LATAM | Remote

Senior AI Developer (Full Stack) LATAM | Remote$4,200-5,800/monthJob DetailsRequired Experience: 6 yrsTerm: 1 year or moreType: Remote (LATAM)Employer Location: Chicago, United StatesTeam Size: From 11 to 50SkillsC#MongoDBNLP (Natural Language Processing)OpenAI IntegrationPrompt EngineeringAugmented Retrieval Generation (RAG)RESTful APIsVector Database.NET Core.NET FrameworkLLM (Large Language Models)AzureMicroservicesAgent-based ModelingEvent-DrivenKnowledge GraphModel Fine-TuningFull Stack DeveloperBack End DeveloperML EngineerAI DeveloperThe PurposeBuild full-stack products powered by AI.We're hiring a Senior AI Developer with a strong full stack background to design and ship production-ready applications that combine modern web development with intelligent automation.You'll work across frontend, backend, and AI layers to solve real-world problems end-to-end.This is a hands-on role for engineers who enjoy shipping fast, owning systems, and using AI to make products meaningfully better.What You'll DoCreate, develop, and manage AI-driven features and systems focused on LLM Integration to provide intelligent, production-ready product experiences.Implement and embed AI functionalities such as large language models, agents, embeddings, and inference pipelines within backend applications and services.Design AI workflows including prompt orchestration, tool invocation, retrieval-augmented generation (RAG), and model routing.Take full responsibility for the AI systems' entire lifecycle—from initial experimentation and prototyping through deployment, monitoring, and ongoing enhancement.Develop scalable APIs and services that securely and dependably deliver AI capabilities to various product interfaces.Work closely with product managers, backend engineers, and designers to convert business challenges into practical AI-powered solutions.Maintain AI system quality by conducting evaluations, testing, observability, and tracking performance metrics.Tackle AI-specific challenges such as reducing latency, optimizing costs, ensuring reliability, mitigating hallucinations, and enforcing safety protocols.Keep up-to-date with the latest AI models, frameworks, and industry best practices, applying them effectively to real-world applications.Plan and integrate AI features aligned with LLM Integration into both product components and backend infrastructure.Construct and sustain AI workflows like prompt orchestration, retrieval augmentation, and agent-based executions to address actual product needs.Design and deploy LLM-enhanced features across backend services and user interfaces, including orchestrating prompts and iterating improvements.Implement and support comprehensive AI workflows (such as matching, vetting, summarization) with attention to observability, testing, and protective measures.What We're Looking ForOver 5 years of professional experience in software engineering, including a minimum of 3 years developing AI-driven systems deployed in production environments.Extensive expertise in integrating large language models (LLMs), machine learning models, or AI services within backend architectures and applications.Deep knowledge of AI system architectural patterns such as Retrieval-Augmented Generation (RAG), intelligent agents, prompt engineering, and workflow orchestration.Proven experience in designing and utilizing APIs tailored for AI-enabled services.Practical skills in assessing model quality, evaluating performance, and ensuring reliability under real-world conditions.Proficient programming abilities in at least one backend language, such as Python, Node.js, Java, or equivalent.Capability to analyze and balance trade-offs involving accuracy, response time, operational cost, and system complexity.Direct experience creating AI-powered functionalities leveraging contemporary AI models or frameworks, particularly those focused on LLM integration.Thorough understanding of design considerations in AI systems, including compromises among accuracy, latency, cost, and dependability.Hands-on practice integrating LLM providers (for example, OpenAI) into full-stack solutions with secure management of prompts and data.Strong grasp of AI system trade-offs related to latency, expenses, and accuracy, along with effective evaluation and monitoring methodologies.Nice-to-HavesHands-on experience with training, fine-tuning, or customizing machine learning models for deployment in production environments.Knowledge of vector databases, embedding techniques, and semantic search methodologies.Understanding of AI safety principles, governance frameworks, and ethical AI practices.Background in developing multi-modal AI systems encompassing text, vision, and speech.Involvement in building an AI-powered hiring platform, including components like AI-based candidate evaluation pipelines, large language model-driven matching and ranking services, and full-stack web and API development.Practical experience creating AI agents for automating workflows in production, including tool integration, function invocation, and implementation of guardrails.Familiarity with Retrieval-Augmented Generation (RAG) approaches—utilizing vector databases, embedding methods, and evaluation techniques—to enhance accuracy and relevance.How You Would FitStrong Ownership – you assume full responsibility from start to finish, focusing not only on tasks but on delivering meaningful results.Clear Communication – you provide context early, express ideas clearly, and simplify complex concepts for your team.Problem Solving – you quickly transform uncertainty into clear, actionable solutions by breaking down challenges effectively.Structural Thinking – you build scalable systems with logical foundations rather than quick fixes.High Velocity – you prioritize continuous progress, deliver iteratively, and understand how momentum drives success.J-18808-Ljbffr