• Design and build AI-powered web applications, integrate LLMs into the platform • Develop automation workflows for research and data processing • Build AI-powered web applications that integrate LLMs and AI models into real product workflows • Integrate OpenAI, Anthropic, Ollama, or other compatible LLM providers into the platform • Build dashboards, search capabilities, AI chat functionality, and data pipelines • Develop automation workflows for research and data processing use cases • Build automations using platforms such as Make.com, n8n, Zapier, or similar orchestration tools • Build backend services and APIs using Python with FastAPI or Node.js with Express • Develop frontend interfaces using React or Next.js • Act as a technical partner to the client, facilitating brainstorming sessions and guiding non-technical stakeholders toward the best solution

Role Description We're looking for a Full-Stack AI Engineer to act as a technical partner and AI-powered full-stack engineer for a fast-moving business operation. This is more than a typical automation role. You will: - Design and build AI-powered web applications - Integrate LLMs into the platform - Architect scalable systems - Develop automation workflows for research and data processing - Serve as a collaborative technical consultant to non-technical stakeholders This is a builder and thinker role. You will: - Make architectural decisions - Suggest better solutions proactively - Guide the client through technical choices with clarity and confidence Comfort with changing requirements and genuine ownership are non-negotiable. If you are a strong full-stack engineer with deep AI and LLM experience who can communicate technical concepts simply and work independently, this role is a strong fit. Qualifications - 3 or more years of experience building and shipping production-grade applications or automation systems - Proven experience building AI-powered applications using LLMs including OpenAI, Anthropic, or Ollama - Strong full-stack engineering skills across Python and JavaScript or TypeScript - Hands-on experience with FastAPI, Node.js or Express, and React or Next.js - Comfortable designing scalable system architecture rather than simply implementing assigned tasks - Strong understanding of API integrations, webhooks, and SaaS connectivity - Excellent written and verbal communication with the ability to explain technical concepts clearly to non-technical audiences - Proactive, ownership-driven, and comfortable adapting quickly when requirements shift - Comfortable working fully remotely and managing technical deliverables independently Requirements - Experience with AI orchestration frameworks such as LangChain, LlamaIndex, or similar (Nice to Have) - Familiarity with data pipeline tooling or lightweight backend infrastructure (Nice to Have) - Background in SaaS product environments or operations-heavy businesses (Nice to Have) - Experience building search or RAG-based systems (Nice to Have) - Prior experience acting as a technical consultant or leading architecture discussions with non-technical clients (Nice to Have) Benefits - You will be paid in USD (bi-monthly: every 15th and 30th) - Paid Time Off in accordance with company policy - Observance of Holidays per company guidelines - 100% remote setup so you can work wherever you're most productive - Direct ownership over AI application architecture and automation infrastructure - Work as a true technical partner with a collaborative, ideas-driven client who values your input How to Apply Please include: - Your updated resume - A portfolio link or examples of AI-powered applications or automation systems you have built - A short Loom video (1 to 2 minutes) walking through a project you built end to end, what technical decisions you made, and how you communicated those decisions to a non-technical stakeholder Only candidates who submit both a portfolio and Loom video will be moved to the next step of the hiring process. Application Process Overview Our comprehensive selection process ensures we find the right fit for both you and our clients: - Initial Application - Submit your application and complete our prequalifying questions - Video Introduction - Record a video introduction to showcase your communication skills and work experience - Role-Specific Assessment - Complete a homework assignment tailored to the position (if applicable) - Recruitment Interview - Initial screening with our talent team - Executive Interview - Meet with senior leadership to discuss role alignment - Client Interview - Final interview with the client team you'd be supporting - Background & Reference Check - Professional reference verification - Job Offer - Successful candidates receive a formal offer to join the team Each stage is designed to evaluate your fit for the role while giving you insights into our company culture and expectations. We'll keep you informed throughout the process and provide feedback at each step.

• Design, develop, and deploy production-grade applications leveraging various LLMs, context optimization, etc. • Architect and implement sophisticated, multi-step and multi-agent workflows using frameworks like LangChain and LangGraph. • Build and optimize RAG pipelines, including implementing and managing embeddings, vector databases, and advanced rerankers to enhance response quality and relevance. • Use code generation applications (e.g. Replit, Cursor, Google AI Studio, Git Hub Copilot in Agent mode, etc.) to create full applications (including frontend and backend), generate tests, perform testing and integrate them in the core product without writing any code. • Lead efforts in LLM fine-tuning (e.g., LoRA, QLoRA) for specific domain knowledge and tasks, and implement strategies for efficiency. • Develop and refine advanced prompt engineering techniques to maximize model performance, consistency, and safety. • Own end-to-end implementation from frontend to the backend. • Expose AI/LLM functionality written in Python using Java services, leverage multi-threading capabilities in Java to augment AI/LLM functionality developed in Python • Utilize AI-powered development tools (e.g., GitHub Copilot, etc.) to efficiently generate, refactor, and optimize high-quality code. • Work closely with team leads managers, QA, product managers and team in the US (this will require the willingness to partially work US working hours)

• Diseñar y construir con alto apalancamiento de IA, un núcleo de software simple, robusto y bien probado. • Construir de punta a punta (full-stack), diseñas e implementas funcionalidades completas del ciclo de renta. • Usar agentes de IA como forma principal de construir. • Revisar y validar críticamente el código propio, del equipo o generado por IA. • Proponer estándares, documentación y mejores prácticas.