Principal Architect – AI

Vaga não está no LinkedIn

🕒 Setembro 16

🇺🇸 Estados Unidos – Remoto (EUA)

⏰ Tempo Integral

🔴 Especialista

🤖 Engenheiro de IA

🦅 Patrocina Visto H1B

Esta empresa já patrocinou vistos H1B no passado.

👻 Score fantasma 11%

O que significa: quão provável esta vaga está aberta sem contratação ativa.Como ler: 60% ou mais significa que achamos que é uma vaga fantasma. Pontuações mais baixas preocupam menos.Como pontuamos: tempo em aberto, republicações, vagas abertas vs tamanho do time, rapidez para fechar vagas, e se o salário está divulgado.Observação: é uma estimativa de dados públicos, não um julgamento da empresa. Vagas reais podem ter pontuação alta, então use como uma dica, não como um fato.

Candidatar-se

Encontrar Vagas Remotas Similares

Configurar Alerta de Email para Novas Vagas

📊 Verifique sua pontuação de currículo para esta vaga

Melhore suas chances de conseguir uma entrevista verificando sua pontuação de currículo antes de se candidatar.

Enviar Currículo

BrightSide

SiteLinkedInTodas as Vagas

51 - 200 funcionários

Fundada em 2010

💼 Consultoria

📦 Logística

🎯 Recrutamento

Consulting • Logistics • Recruitment

A BrightSide é uma empresa argentina de consultoria em SAP e alocação de profissionais de TI que ajuda organizações a formar e expandir equipes de projeto de tecnologia, fornecendo talentos especializados e sêniores de TI, além de oferecer serviços completos em SAP. Eles oferecem aumento de equipe de TI, recrutamento e seleção, atribuições remotas ou presenciais, e diversos serviços SAP, incluindo implementações e migrações para S/4HANA, desenvolvimento em ABAP e Fiori/UI5, integrações, BASIS e segurança em SAP, além de planos de suporte e manutenção. A BrightSide foca na entrega rápida, modelos de contratação flexíveis e suporte de longo prazo para clientes corporativos.

Descrição

• Own the design and build of Brightside’s AI agent platform • Design and own the multi-agent orchestration layer, including session supervisor, domain clusters, escalation arbiter, and conversation manager • Define agent routing logic, context sharing, tool use, and latency budgets across 18+ agents • Architect the real-time pipeline from Amazon Connect through Contact Lens, Kinesis, Lambda, Bedrock, and WebSocket push to the Financial Assistant panel • Own dual-mode agent architecture for human-assisted coaching and autonomous client conversations • Define model selection and routing across low-latency and reasoning-intensive agent tiers • Govern prompt architecture, including structured agent prompt standards, runtime domain knowledge injection, and conditional output formatting • Build and own the evaluation harness for schema validation, behavioral regression testing, and latency profiling • Design the domain knowledge base across 8 domains and 49 use case types • Own the AI platform data model for client financial profiles, cases, goals, options, outcomes, and financial impact measurement • Architect the CRM synchronization layer, including real-time field writes after Financial Assistant confirmation and human correction logging • Define canonical data models across clients, employers, financial products, and outcomes • Ensure data integrity across Aurora PostgreSQL and Aurora MySQL • Own AWS Bedrock-native inference infrastructure, including asynchronous invocations, Knowledge Bases, and RAG pipelines • Design the session state layer using ElastiCache Redis and DynamoDB • Define AI governance standards for model evaluation, monitoring, explainability, and compliance • Evaluate and guide decisions on model providers, orchestration frameworks, and platform tooling • Work directly alongside Jacky Chiu and the engineering team to architect and ship production systems • Debug Bedrock invocations, profile latency spikes, and review schema changes

🎯 Requisitos

• 10+ years in software engineering or systems architecture, with significant hands-on experience in the last 3 years • Production experience building real-time AI systems operating on a per-turn, sub-second latency budget • Hands-on experience with Amazon Bedrock, AWS Lambda, and Kinesis • Multi-agent system design experience, including orchestration patterns, agent handoff, context sharing, and structured output validation • Strong data architecture foundation, including relational modeling, event-driven systems, and CRM data patterns • Experience in a regulated environment such as fintech, financial services, or healthcare, with understanding of privacy and compliance requirements • Comfortable operating in a small, fast-moving team where you design and build • Experience building voice or conversation intelligence systems • Hands-on experience with Amazon Connect and Contact Lens • Background in conversational AI product companies such as Cresta, Observe.AI, Cogito, Replicant, or similar • Experience with LLM prompt engineering at a systems level, including eval harnesses, versioned prompt governance, and regression testing • Prior experience as a lead architect at a Series B-D company • Comfortable forming, explaining, and updating technical opinions • Oriented toward production outcomes • Comfortable debugging Bedrock invocations, profiling latency spikes, and reviewing schema changes • Able to balance experimentation with rigor in a regulated fintech environment

🏖️ Benefícios

• Inspiring careers • Great life/work balance • Meaningful work with direct impact on working families • Opportunity to see a growing start-up from the inside out