Senior AI Architect & Engineer

OVERVIEW Senior AI Architect & Engineer Remote | The m ain office location for this role located in Alpharetta, Georgia. At Alera Group, our colleagues help businesses protect their assets, manage risk, and plan confidently for the future. We’re seeking a Senior AI Architect & Engineer who will support risk strategy, client service excellence, and operational accuracy through transofrmational technology deliverables. About Alera Group Alera Group was founded in 2017 and has grown to become the 14th largest broker of U.S. business. We are passionate about our clients’ success in the areas of Employee Benefits, Property and Casualty Insurance, and Financial Services. With a network of offices nationwide, our commitment to collaboration allows us to offer national resources combined with local service. Why Alera Group Meaningful Impact: Help clients and employees navigate benefits programs that drive retention, engagement, and satisfaction Growth & Learning: Opportunities to deepen your expertise and gain exposure to a variety of clients and industries Collaborative Culture: Work in a team-oriented environment that values accountability, partnership, and the principles of The Collaborative Way RESPONSIBILITIES What You’ll Do / Your Impact Agent Stack Operations • Own day-to-day operations of the 18-agent LangGraph stack: uptime, performance monitoring, output quality review, and continuous improvement cycles • Instrument and manage observability in LangSmith; define SLA thresholds and build alerting protocols for production agent failure modes • Expand the agent library from 18 to 12–15 additional agents by end of Year 2 as ETP verticals scale • Maintain the Notion knowledge base as the primary training and context data source for agent accuracy and carrier appetite matrices Platform Integration • Build the Atlas API integration layer connecting ETP intelligence outputs to the Applied Epic AMS workflow — the single highest-impact integration in the current roadmap • Navigate the Applied Systems API licensing terms in coordination with Alera's CIIO; design the middleware architecture that survives the licensing resolution outcome • Connect the embedded intake flow to Attio CRM for automated pre-qualified prospect pipeline delivery • Develop and maintain REST API integrations across the ETP tool stack: Attio, Airtable, Notion, Beehiiv, and carrier data feeds SaaS Commercialization Readiness • Collaborate with the Enterprise Architect on the multi-tenancy architecture decision — the blocking issue between Atlas as an internal tool and Atlas as a licensed SaaS product • Prepare technical documentation, API schemas, and integration guides required for the external licensing pilot • Support the Head of SaaS & Product Commercialization (Wave 2 hire) with platform readiness assessments and licensing architecture options Data Infrastructure • Own the PostgreSQL + pgvector data layer: schema design, query optimization, and vector index performance for agent retrieval accuracy • Design and operate data pipelines for intelligence ingestion — regulatory filings, carrier appetite signals, market intelligence — that feed agent context • Build S3-equivalent durable data architecture on A zure Blob ensuring source-of-truth data is decoupled from any single compute or query layer Azure Infrastructure & DevOps • Manage Azure infrastructure supporting Atlas: CI/CD pipelines, container orchestration, environment parity between development and production • Implement OpenTelemetry-based APM across the agent stack and API integration layer for production-grade observability • Coordinate with Alera's Enterprise Architecture team on platform-level decisions affecting multi-tenancy, data residency, and licensing architecture QUALIFICATIONS What You Bring Required • Production Python development — FastAPI or equivalent; REST API architecture at scale • LangGraph, LangSmith, or equivalent agentic AI orchestration framework — production deployment, not prototyping • Cloud infrastructure ownership — design, deploy, and operate distributed cloud systems under resource constraints • PostgreSQL or comparable RDBMS — schema design, indexing, query optimization for high- throughput systems • Event-driven or queue-backed parallel processing architecture — SQS, Celery, or equivalent • CI/CD pipeline management — Docker, containerized deployment, environment management • Demonstrated ability to ship in resource-constrained environments — startup or acquisition- integrated team context Strongly Preferred • Azure infrastructure experience (.NET 10 stack, Azure Blob, Azure-native CI/CD) • LLM-assisted development workflows as a first-class practice — Claude Code, GitHub Copilot, or equivalent • Vector database experience — pgvector, Pinecone, or Weaviate — for RAG pipeline architecture • Experience navigating enterprise API licensing or integration partnerships with third-party platform vendors • OpenTelemetry or APM tooling for distributed system observability Plus/ a Bonus if you have: • End-to-end ownership of a production application: architecture, implementation, deployment, and operations • Experience in post-acquisition integration — navigating technology transitions across incompatible stacks • DoD or government systems background (relevant to federal program tracks: NSIP, MCIP) • Insurance, financial services, or regulated industry data experience ADDITIONAL INFORMATION Benefits: Alera Group offers comprehensive benefits including medical, dental, vision, life and disability coverage, 401(k), generous PTO, and more. Work Model: This role is Remote Professional Development – Alera Group Academy At Alera Group, growth isn’t left to chance. Through Alera Group Academy , we provide structured development opportunities designed to help you expand your expertise and build a meaningful career. You’ll have access to: Role-specific learning paths Leadership development programs Technical and compliance training Industry certifications and continuing education support Peer learning and knowledge-sharing communities Whether you’re deepening technical expertise or preparing for leadership, we’re invested in helping you grow. Licensure & Certifications (If Applicable) This position may require: Active State Property & Casualty License Ability to obtain required licensure within 12 months of hire Ongoing continuing education to maintain active status We're an equal opportunity employer. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status, or any other protected class. Alera Group is committed to protecting your privacy. Please review our Privacy Policy to understand what personal information we may collect and use as part of your application process. #LI-WZ1 #LI-Remote Location Type Remote What You'll Do / Your Impact Agent Stack Operations • Own day-to-day operations of the 18-agent LangGraph stack: uptime, performance monitoring, output quality review, and continuous improvement cycles • Instrument and manage observability in LangSmith; define SLA thresholds and build alerting protocols for production agent failure modes • Expand the agent library from 18 to 12-15 additional agents by end of Year 2 as ETP verticals scale • Maintain the Notion knowledge base as the primary training and context data source for agent accuracy and carrier appetite matrices Platform Integration • Build the Atlas API integration layer connecting ETP intelligence outputs to the Applied Epic AMS workflow - the single highest-impact integration in the current roadmap • Navigate the Applied Systems API licensing terms in coordination with Alera's CIIO; design the middleware architecture that survives the licensing resolution outcome • Connect the embedded intake flow to Attio CRM for automated pre-qualified prospect pipeline delivery • Develop and maintain REST API integrations across the ETP tool stack: Attio, Airtable, Notion, Beehiiv, and carrier data feeds SaaS Commercialization Readiness • Collaborate with the Enterprise Architect on the multi-tenancy architecture decision - the blocking issue between Atlas as an internal tool and Atlas as a licensed SaaS product • Prepare technical documentation, API schemas, and integration guides required for the external licensing pilot • Support the Head of SaaS & Product Commercialization (Wave 2 hire) with platform readiness assessments and licensing architecture options Data Infrastructure • Own the PostgreSQL + pgvector data layer: schema design, query optimization, and vector index performance for agent retrieval accuracy • Design and operate data pipelines for intelligence ingestion - regulatory filings, carrier appetite signals, market intelligence - that feed agent context • Build S3-equivalent durable data architecture on A zure Blob ensuring source-of-truth data is decoupled from any single compute or query layer Azure Infrastructure & DevOps • Manage Azure infrastructure supporting Atlas: CI/CD pipelines, container orchestration, environment parity between development and production • Implement OpenTelemetry-based APM across the agent stack and API integration layer for production-grade observability • Coordinate with Alera's Enterprise Architecture team on platform-level decisions affecting multi-tenancy, data residency, and licensing architecture What You Bring Required • Production Python development - FastAPI or equivalent; REST API architecture at scale • LangGraph, LangSmith, or equivalent agentic AI orchestration framework - production deployment, not prototyping • Cloud infrastructure ownership - design, deploy, and operate distributed cloud systems under resource constraints • PostgreSQL or comparable RDBMS - schema design, indexing, query optimization for high- throughput systems • Event-driven or queue-backed parallel processing architecture - SQS, Celery, or equivalent • CI/CD pipeline management - Docker, containerized deployment, environment management • Demonstrated ability to ship in resource-constrained environments - startup or acquisition- integrated team context Strongly Preferred • Azure infrastructure experience (.NET 10 stack, Azure Blob, Azure-native CI/CD) • LLM-assisted development workflows as a first-class practice - Claude Code, GitHub Copilot, or equivalent • Vector database experience - pgvector, Pinecone, or Weaviate - for RAG pipeline architecture • Experience navigating enterprise API licensing or integration partnerships with third-party platform vendors • OpenTelemetry or APM tooling for distributed system observability Plus/ a Bonus if you have: • End-to-end ownership of a production application: architecture, implementation, deployment, and operations • Experience in post-acquisition integration - navigating technology transitions across incompatible stacks • DoD or government systems background (relevant to federal program tracks: NSIP, MCIP) • Insurance, financial services, or regulated industry data experience