Senior Ai Engineer (Avellaneda)

About the RoleWe are looking for a talented AI Engineer to design, build, and deploy intelligent agents that can understand, reason, and act on behalf of our customers. You will work at the cutting edge of applied AI—combining LLMs, retrieval-augmented generation (RAG), knowledge graphs, MCPs, and autonomous agent frameworks—to solve real-world customer engagement problems at scale. This is a highly collaborative and impact-driven role, working closely with product managers, designers, data scientists, and engineers.Your ResponsibilitiesDesign and implement AI agentic architectures tailored to customer engagement and automation use cases.Develop and maintain pipelines for agent reasoning, memory, planning, and tool use—integrating LLMs, Agents, RAG systems, MCPs, and external APIs.Evaluate models and agents to improve performance, reliability, and alignment.Collaborate on building a robust agent framework with support for multi-step workflows and dynamic goal execution.Optimize agent cost, latency, and safety for production environments.Monitor, test, and continuously improve deployed agents based on customer feedback and analytics.Stay ahead of emerging trends in agent-based AI and proactively bring innovative ideas into our products.Your ProfileSolid experience (8+ years) in software engineering with a focus on AI/ML systems.Hands‐on experience with LLMs, RAG pipelines, MCPs, context engineering, prompt engineering, or autonomous agent frameworks (e.g., LangChain/LangGraph, CrewAI, AutoGPT, or similar). Strong programming skills in Python (preferred) and familiarity with cloud environments (AWS preferred). Good understanding of information retrieval, knowledge graphs, and/or planning & reasoning in AI.Familiarity with MLOps, experiment tracking, and model deployment practices.Experience working with unstructured text data and NLP tasks.Excellent problem‐solving skills, with a bias towards delivering results.Strong communication and teamwork abilities in a fast‐paced, collaborative environment.Nice to have: experience with reinforcement learning or agent simulation environments; background in human‐in‐the‐loop systems or AI safety/alignment; contributions to open‐source agent frameworks or NLP libraries.BenefitsPayment in USDA truly versátil work scheduleNon‐Working Pay Days PolicyLearning BudgetAn opportunity to help create change in the industryAnd more #J-*****-Ljbffr Postúlate en Kit Empleo: kitempleo.com.ar/empleo/qjz74