• Backend Development: Contribute to the design, development, and optimization of FIGS backend services, aiming for resilience, performance, and scalability. • Cloud & Kubernetes Integration: Assist in integrating our applications and services within AWS and Kubernetes, leveraging tools such as Flux and Argo for GitOps workflows. • Infrastructure as Code: Support the use of Terraform or AWS CDK to efficiently create, manage, and orchestrate cloud infrastructure components. • Database Management: Aid in building robust database solutions with PostgreSQL and optimize search functionalities with ElasticSearch. • Architectural Assistance: Participate in architectural discussions, focusing on scalability, performance, and reliability. • Team Collaboration: Work closely with fellow engineers, absorbing best practices, especially concerning Java and cloud-native technologies. • Operational Support: Assist in engineering decisions, considering aspects from cost efficiency to data security under the guidance of senior leadership.

• Designing and implementing scalable backend services for AI RAG systems. • Building and maintaining FastAPI-based APIs. • Creating and optimizing CI/CD pipelines. • Contributing to vector storage and chunking strategies. • Ensuring reliability, testing, and production readiness. • Proactively improving backend architecture and infrastructure.

• Diseñar, implementar y gestionar infraestructura cloud en AWS, utilizando IaC (Terraform, CloudFormation) • Mantener y mejorar pipelines CI/CD con GitHub Actions, AWS CodePipeline, Jenkins o ArgoCD • Implementar sistemas de observabilidad mediante CloudWatch, Prometheus/Grafana, ELK u OpenTelemetry • Gestionar y operar servicios en Kubernetes (EKS), ECS o Fargate • Desarrollar arquitectura backend para servicios de AI Verification y ChatGPT-like services con Python y FastAPI • Diseñar y construir soluciones siguiendo DDD y TDD • Desarrollar servicios LLM-as-a-judge usando HuggingFace, Transformers, SpaCy, NLTK, BM25 • Optimizar latencia mediante ONNX, cuantización y otras técnicas de compresión • Desplegar y mantener soluciones AI multi‑servicio en Kubernetes con observabilidad avanzada • Construir pipelines CI/CD para despliegue continuo de microservicios de IA • Diseñar y mantener soluciones RAG de alta carga: Ingestión de datos, Brokers de mensajería, Retrieval services, Integración con herramientas tipo agentes (LangChain, Unstructured), Azure OpenAI, Embeddings, Azure Cosmos DB, Service Bus, App Services • Realizar prompt engineering avanzado (Chain-of-Thought, few-shot learning, multi‑LLM) • Evaluar nuevas arquitecturas, agentes y soluciones de distintos cloud providers • Analizar seguridad, modularidad y escalabilidad de arquitecturas basadas en IA.

• Atuar como Desenvolvedor(a) de aplicações e frameworks de arquitetura Web • Elaborar especificações técnicas com base especificação funcional • Revisão de soluções e implementações técnicas; • Atuação em equipes multidisciplinares, seguindo metodologia ágil; • Realizar análise\troubleshooting de problemas em ambientes de QA\HML e Produção • Criação de APIs, atuação com arquitetura em microserviços; • Desenvolvimento e manutenção de aplicações web; • Realizar a manutenção e criação de novas funcionalidades; • Aplicar melhores práticas de documentação de código desenvolvido; • Buscar novas ferramentas e técnicas para a melhoria contínua de nossos sistemas; • Desenvolvimento de funcionalidades no Back-End;