• Collect, evaluate, and prioritize feature requests from users, sales, and market insights. • Conduct market research and benchmark competitors, focusing on API platforms, AI technologies (LLMs, RAG, vector search), and user experience in trust-focused products. • Develop detailed user stories and acceptance criteria for APIs (REST/GraphQL), SDKs, webhooks, and AI-powered functionalities. • Collaborate with the VP of Product and engineering leads to prioritize features in line with the overall product strategy. • Plan and maintain the product roadmap, adjusting priorities based on market trends and feedback. • Manage a structured product backlog with clear priorities. • Oversee feature releases following CI/CD practices. • Lead internal testing sessions to validate usability, accessibility, and quality. • Analyze feature performance using tools like Mixpanel and recommend improvements. • Keep product documentation current, including API references, wireframes, and release notes. • Work alongside marketing and customer success teams to ensure smooth product launches and communications.

• Arquitectar y construir sistemas de IA agentica utilizando frameworks como LangChain, AutoGen, DSPy, CrewAI o herramientas de orquestación desarrolladas a medida. • Diseñar flujos de trabajo modulares y orientados a objetivos que permitan a los agentes autónomos planificar tareas, colaborar con otros agentes e interactuar con herramientas externas. • Implementar patrones de agentes como planner–executor, ReAct, reflection y self‑verification. • Desarrollar estrategias de prompting avanzadas, incluyendo chain-of-thought, tree-of-thought, salidas estructuradas y versionado de prompts. • Construir e integrar sistemas de memoria (corto plazo, largo plazo, episódica) para soportar persistencia del contexto y capacidades de aprendizaje. • Integrar LLMs (OpenAI, Anthropic, Mistral, Cohere, DeepSeek, modelos de código abierto) con entornos de ejecución como Python, Bash, SQL, APIs REST y herramientas de automatización de navegador. • Implementar tool calling/funciones, orquestación de APIs y agentes de ejecución de código. • Diseñar y optimizar pipelines de RAG utilizando bases de datos vectoriales y búsqueda híbrida. • Optimizar el rendimiento de agentes para baja latencia, fiabilidad, eficiencia de costes y escalabilidad en aplicaciones reales como agentes de investigación, copilotos de programación o asistentes de planificación. • Desplegar y mantener sistemas agenticos en producción utilizando Docker, pipelines de CI/CD e infraestructura en la nube. • Monitorizar el comportamiento de los agentes, registrar trazas de ejecución y pasos de razonamiento (cuando corresponda) y mejorar continuamente la robustez y alineación del sistema. • Colaborar estrechamente con científicos de datos, ingenieros de software, equipos de producto y diseñadores UX para entregar soluciones de IA de alto impacto. • Implementar flujos de trabajo con humanos en el circuito (HITL) para supervisión, retroalimentación y autonomía segura.

• Understand, develop, & support deep math analytics in Explainable AI Engines • Build, evolve, verify, and validate data processing pipeline segments • Support scalable deployment of the AI • Integrate Explainable AI with LLM tools for Agentic AI experience • Collaborate with the cloud software team and occasionally with customers • Document Explainable AI for customer users and internal software developers

• Design, secure, extend, and customize system prompts (e.g., chat history, instructions, rules); • Evaluate the impact of prompt changes and continuously improve LLM usage scenarios while analyzing risks and benefits. • Design and optimize retrieval pipelines, including document chunking, embedding generation, and ranking strategies. • Build and maintain solutions using vector databases (e.g., FAISS, Weaviate, Pinecone) or Postgres with pgvector, to enable accurate and context-aware responses. • Implement advanced context window optimization, memory strategies, and token efficiency techniques to ensure scalable and cost-effective LLM interactions. • Evaluate new LLM releases, monitor response quality and consistency, and build automated evaluation pipelines to assess performance across use cases. • Design and implement prompt injection protection, output filtering, and policy enforcement mechanisms to ensure safe and compliant AI behavior in enterprise environments. • Develop and expose AI capabilities via scalable APIs, ensuring proper integration into existing systems and workflows. • Design and manage serving layers for LLM applications, addressing scaling strategies, latency considerations, and reliability in both cloud and on-prem environments. • Implement logging, monitoring, and alerting mechanisms to ensure visibility into system performance, usage patterns, and failures. • Develop prototype and production-level Python code to support AI features, ensuring reliability and maintainability aligned with product requirements. • Stay up to date with the latest techniques in reasoning, chaining, and context optimization; contribute to AI Labs community discussions and share findings with the Data Science team.