Senior Backend & Ai Engineer

Senior Backend & Ai Engineer - Detalhes da Vaga. ● You’ll build scalable backend services while helping integrate AI capabilities into news systems, including LLM orchestration, fine-tuning, RAG, and intelligent automation. ●You’ll collaborate with engineering teams and global stakeholders across multiple regions, helping transform how AI and automation power the next generation of newsroom platforms. ●The RoleBackend Engineering: Build and maintain scalable services using Node. ●Js, TypeScript, and Express. ●Js within a distributed microservices environment. ●AI & LLM Integration: Develop AI-powered services using LangChain, prompt engineering, LLM orchestration, and model fine-tuning. ●RAG & NLP: Design and maintain Retrieval Augmented Generation (RAG) systems that ground AI outputs in trusted news content, with a strong understanding of embeddings and tokenization. ●Model Strategy: Work with models such as Google Gemini, OpenAI, and Anthropic, selecting the right model based on performance, capabilities, and cost. ●MLOps & Observability: Monitor AI and backend performance, including latency, throughput, errors, model quality, bias, toxicity, and concept drift. ●Distributed Systems: Build secure integrations across internal REST/gRPC APIs, third-party vendors, and microservices. ●DevOps & Infrastructure: Containerize services with Docker, manage CI/CD through CircleCI, and support infrastructure using Terraform. ●Global Collaboration: Work closely with distributed engineering teams and stakeholders, presenting technical solutions and contributing to a highly collaborative, asynchronous environment. ●The "Must-Haves"Backend Engineering: 5+ years of professional backend development experience, ideally within distributed or microservices environments. ●Node. ●Js / TypeScript: Strong hands-on expertise with Node. ●Js, TypeScript, and Express. ●Js. ●Python: Basic to intermediate Python experience for AI/ML development and model-related tasks. ●LangChain: Hands-on experience with LangChain is mandatory. ●AI / LLMs: Strong understanding of NLP, tokenization, embeddings, prompt engineering, LLM fine-tuning, and RAG architectures. ●Cloud & DevOps: Experience with Docker, CI/CD pipelines, and at least one major cloud provider — Google Cloud preferred, AWS acceptable. ●Microservices: Strong understanding of distributed and microservice architectures. ●Global Collaboration: Comfortable working asynchronously across multiple time zones and collaborating with international stakeholders. ●The "Bonus" SkillsInfrastructure as Code: Experience with Terraform. ●Legacy Technologies: Familiarity with PHP. ●Media & Publishing: Experience working in media, publishing, journalism, or newsroom technology. ●GTM Experience: Exposure to startup environments and Go-to-Market strategies. ●Advanced MLOps: Experience with model evaluation, validation, monitoring, and production AI/ML pipelines. ●Personal TraitsAI-Minded Engineer: Excited about applying LLMs and emerging AI technologies to real-world products and workflows. ●Backend Problem Solver: Enjoys building reliable, scalable services and solving complex distributed-system challenges. ●Pragmatic Technologist: Able to evaluate models, tools, and approaches based on technical requirements, quality, and cost. ●Strong Communicator: Comfortable presenting ideas, explaining technical decisions, and working with stakeholders across different regions. ●Self-Driven: Thrives in a remote, asynchronous environment and takes initiative without constant direction. ●Global Collaborator: Enjoys working across cultures, time zones, and engineering teams to deliver high-impact solutions. ●. Requisitos para participar do processo. ● . O que oferecemos.