• Liderar a integração técnica da API da Anthropic (Claude) na plataforma IARA e na infraestrutura AWS do cliente; • Projetar e implementar abstrações de acesso a modelos para padronização do consumo em ambientes multi-cloud (AWS + Azure/GCP); • Garantir interoperabilidade entre diferentes provedores de modelos com governança e rastreabilidade centralizadas; • Definir padrões técnicos para consumo de LLMs, incluindo gestão de contexto, versionamento de modelos e estratégias de fallback entre provedores; • Atuar em conjunto com times de segurança para assegurar conformidade e governança no uso de modelos em produção; • Contribuir tecnicamente para o roadmap da plataforma com foco em escalabilidade, operação e padronização; • Produzir documentação arquitetural de referência e conduzir revisões e transferências técnicas com os times envolvidos; • Atuar como referência técnica em arquitetura de IA generativa e integração de modelos foundation em larga escala.

Role Description We are looking for a Salesforce AI Integration Architect to design and build enterprise integrations between internal AI platforms and Salesforce Agentforce environments, scaling autonomous AI workflows across distributed systems. The role requires deep expertise in Salesforce customization, LLM orchestration, and scalable distributed system design. - Architect end-to-end integrations between internal AI platforms, enterprise data systems, and Salesforce Agentforce environments; - Design scalable, secure, and resilient distributed system architectures supporting autonomous AI workflows; - Define integration strategies leveraging REST APIs, gRPC, event-driven architectures, and Salesforce-native capabilities; - Design and optimize modular agentic AI systems through specialized micro-agent delegation; - Build orchestration patterns for multi-step AI workflows, autonomous routing systems, and semantic tool execution; - Apply best practices around prompt engineering, context management, token conservation, and LLM orchestration; - Develop and enhance integrations using Salesforce Flows, Invocable Apex methods, APIs, connectors, and custom prompt templates; - Enable complex backend processes to be exposed as intelligent agentic tools within Salesforce ecosystems; - Collaborate with cross-functional teams to maintain unified API contracts and semantic consistency across enterprise systems; - Author architectural decision records documenting technical trade-offs, constraints, and high-level requirements; - Evaluate and select integration patterns including traditional APIs, Model Context Protocol, and Agent-to-Agent communication models; - Balance performance, latency, scalability, reasoning overhead, and data sensitivity considerations in architectural decisions; - Establish authentication boundaries, trust layers, and governance guardrails for AI-enabled enterprise systems; - Ensure compliance with enterprise security standards, data governance policies, and secure data exposure practices; - Partner with security and platform teams to maintain reliable and trustworthy autonomous agent execution. Qualifications - 6+ years of experience designing enterprise integrations and distributed system architectures; - Hands-on experience integrating systems with Salesforce; - Deep expertise with Apex methods, advanced Salesforce Flows, custom prompt templates, and Salesforce APIs and connectors; - Strong experience with REST APIs, gRPC, event-driven architectures, and enterprise synchronization patterns; - Solid understanding of AI and LLM concepts including prompt engineering, context management, token optimization, multi-step AI workflows, agent orchestration, and semantic routing systems; - Experience designing scalable and secure distributed systems; - Strong understanding of authentication, security, trust boundaries, and data governance; - Experience documenting architecture decisions, trade-offs, and technical strategy; - Excellent collaboration and communication skills across engineering, platform, data, and security organizations; - Upper-intermediate English level. Requirements - Experience with Model Context Protocol (MCP); - Experience with Agent-to-Agent (A2A) integrations; - Experience with MuleSoft or enterprise middleware platforms; - Familiarity with Salesforce Agentforce; - Experience building or managing autonomous AI agents or micro-agent ecosystems; - Experience with semantic tool discovery or AI-native integrations; - Knowledge of Salesforce Bulk APIs and Salesforce Connect; - Experience operating within large-scale enterprise AI environments. Benefits - Remote work & local connection: Work where you feel most productive and connect with your team in periodic meet-ups. - Legal presence in India: Full local compliance and structured work environment. - Competitive compensation in INR: Dedicated budgets for growth, education, and wellness. - Innovative projects: Work with modern technologies and global clients.

• Provide architectural oversight across AI/ML projects to ensure consistency, performance, and maintainability • Evaluate and select AI technologies, frameworks, cloud services, vector databases, LLM orchestration frameworks, and tooling • Support development teams on model selection, training pipelines, prompt engineering, fine-tuning, RAG (Retrieval-Augmented Generation), and evaluation methodologies • Mentor engineers, analysts, and product teams on AI best practices.

Role Description A well-funded AI company in the healthcare infrastructure space is building the engine that automates some of the most complex workflows in health plan operations. This role exists because the product is working and the team needs a senior engineer who can own significant parts of the AI architecture independently. In the first year, you will go from shipping production pipelines to being the person who defines how the company builds LLM-powered systems at scale. - Architect and ship LLM-powered pipelines that automate complex multi-step clinical decision workflows end-to-end. - Build and maintain back-end services in Python that integrate directly with enterprise health systems (FHIR, HL7, EDI). - Own the quality and reliability of AI outputs through evaluation frameworks, structured outputs, and production monitoring. - Drive integrations with external enterprise environments, handling compliance constraints and audit requirements that come with healthcare data. - Translate requirements from product and customer success teams into scoped technical solutions, working directly with non-technical stakeholders when needed. - Operate across the stack from RAG and document pipelines through to cloud infrastructure and observability tooling. Qualifications - 5+ years of software engineering experience, with at least 2 years shipping AI/ML systems in production (not research or internal tooling). - Hands-on experience building and deploying LLM applications: prompt engineering, RAG pipelines, fine-tuning, eval harnesses. - Strong Python back-end skills: FastAPI, async patterns, typing, pytest. - Experience with cloud infrastructure on AWS, GCP, or Azure. - Proven ability to work with enterprise integration requirements including compliance, auditability, and security constraints. - Comfortable scoping and communicating technical solutions directly with clients or non-technical stakeholders. Nice to Have - Prior work in healthcare systems or HIPAA-governed environments. - Experience with FHIR, HL7, or EDI data formats. - TypeScript, Next.js, or front-end exposure. - Monorepo experience at scale. Tools and Stack - Python - FastAPI - PostgreSQL - Temporal - Redis - AWS (RDS, S3, Bedrock, IAM) - Kubernetes - Terraform - Docker - GitHub Actions - Pydantic AI - OpenAI - Google Gemini - OpenTelemetry - Prometheus - Grafana - Sentry - Logfire - PostHog Details - Location: Remote, Latin America - Time Zone: US overlap expected (confirm window with client) - Salary: Competitive — share your expectations when you apply. - Type: Full-time - Start: ASAP Company Description An early-stage AI company automating utilization management and clinical review workflows for health plans, TPAs, and medical management companies. They integrate directly into existing enterprise systems and operate in a regulated environment where accuracy and auditability are non-negotiable. Small, focused team building infrastructure that is already in production at real clients.