Role Description What your day-to-day work as a Sr. AI Engineer looks like: - Create solutions for customers: Architect and implement intelligent LLM-powered ETL pipelines from scratch to transform unstructured client data into concrete, structured solutions. - Build individual agents: Develop autonomous, multi-agent systems using state-of-the-art frameworks to automate complex, multi-step human business processes. - Keep the quality high: Design and maintain robust evaluation frameworks to systematically quantify AI performance and serve as the gatekeeper of quality for production systems. - Own the whole cycle: Build and deploy high-performance RAG systems and wrap the AI logic into performant, production-ready microservices (e.g., FastAPI). - Grow with your team: Actively engage in creative brainstorming sessions and technical design discussions with teammates to challenge assumptions, jointly solve problems, and grow the team's collective knowledge. Qualifications - Fluent English: we're an English-only company. - 2+ years of professional working experience as an engineer (5+ years gets you closer to the "senior" bar). - Strong Python: at least 2 years of real, daily use. - Hands-on LLM experience: ideally 1–3 years of actually shipping LLM-powered features (not just notebooks). - Experience building AI workflows / Agents: multi-step, multi-agent, or otherwise non-trivial orchestration. - RAG systems in production: you've designed retrieval, evaluated it, and made it fast and reliable. - Shipped to real customers: you've built things that real, paying users actually use. Side-project demos don't count here. - Good communicator: happy in async text (Slack) and on calls. You don't disappear for a week into a branch. - Genuinely curious about AI: you can talk us through a recent paper, model, or architectural shift that changed how you think about building systems, and why it mattered to you. - Bonus: you have a cat. (Optional. We don't discriminate against dog people. Much.) Benefits - Remote work: Work from home or wherever you like; we are a 100% remote company. - Flexible working hours: Work when you feel it. It's your life. - Challenging projects: Work on challenging projects with meaningful impact for our customers. - Amazing, creative team: Supportive, curious, open-minded. We joke around a lot but we're serious about the quality of our work. - Continuous learning budget: We pay for your experiments and your side quests. - Enthusiastic AI Engineers: We share a deep passion for tech and AI. We love to learn, grow our skills, and have fun while doing it. - Fault-tolerant culture: Mistakes are part of learning. We make them, we learn, we move on. No blaming, no negative feelings — maybe a few jokes. - ...and yes, you do get a Claude Code subscription.

• Design the end-to-end architecture of the conversational agent using: LLMs, RAG, tool-calling, orchestration, guardrails. • Build and deploy AI services using Python and FastAPI. • Design secure and resilient integrations with: core systems, Salesforce or similar, APIs, cloud services. • Define strategies for: context engineering, retrieval, embeddings, AI observability. • Implement best practices for resilience, security, and troubleshooting. • Collaborate with Backend, Cloud, Architecture, and Product teams. • Lead technical standards, code reviews, and architecture documentation.

• Liderar la definición técnica, arquitectura e implementación de capacidades de Inteligencia Artificial. • Diseñar la arquitectura AI/LLM del proyecto alineada con estándares enterprise. • Liderar la implementación de servicios AI utilizando Python y frameworks modernos. • Diseñar integraciones seguras y resilientes entre modelos AI, APIs y sistemas enterprise. • Definir estrategias de Prompting Retrieval Embeddings Orchestration Observabilidad AI. • Guiar decisiones de performance, escalabilidad y optimización de costos en workloads AI. • Diseñar pipelines AI y flujos de inferencia sobre GCP. • Implementar APIs y servicios AI utilizando Python/FastAPI. • Liderar troubleshooting relacionado con respuestas, latencia, calidad y observabilidad de modelos. • Colaborar con equipos Backend, Frontend, Cloud y Arquitectura. • Definir estándares técnicos, realizar code reviews y promover buenas prácticas de AI Engineering. • Documentar arquitectura, ADRs y decisiones técnicas vinculadas a AI.

• Define and execute the long-term product strategy for Semiotic.ai’s micropayments platform. • Partner with the CEO and executive team to align product direction with company vision and funding goals. • Translate complex technological capabilities into a clear roadmap, ensuring alignment with market trends and customer needs. • Conduct deep market research and user discovery to understand the evolving landscape of micropayments, DeFi, and autonomous transactions. • Continuously assess customer sentiment, ecosystem demand, and competitor positioning to guide product direction. • Develop strong relationships with key partners, developers, and early adopters. • Own the full lifecycle of the micropayments product—from concept to launch to iteration. • Collaborate with cross-functional teams (engineering, design, research, partnerships) to deliver high-quality, scalable solutions. • Establish KPIs and success metrics for product performance and adoption. • Build, mentor, and lead a high-performing product organization to scale with the company’s growth. • Foster a culture of ownership, innovation, and data-informed decision-making. • Support fundraising efforts by crafting compelling product narratives and contributing to investor discussions. • Collaborate with marketing and partnerships to design go-to-market strategies that drive adoption and visibility.