Himarley
Principal AI Platform Engineer
Hybrid - Boston, MA · Principal
Sponsorship not specifiedDetected 37 days ago
RailsPostgreSQLDynamoDBAWSTerraformPlatform EngineeringRESTOAuthLLMsAgentic AICommunication
About the role
- Insurance touches people during some of the most challenging moments in their lives.
- If you believe insurance can combine operational excellence and automation with a human touch, we'd love to meet you.
- Bedrock for models, Cognito for auth, CDK or Terraform for everything else.
Responsibilities
- Build the AI Operations platform on AWS: Own the hosting, deployment, and infra-as-code layer for every internal agent and tool we run.
- Architect the registries and catalogs: Design and build the Accountability Registry (people, ownership, roles), the Agent Registry (identity, permissions, data scope, audit trail), and the Tool & App Catalog (discover, register, approve).
- Solve the identity-inheritance problem: An agent acts with the inherited permissions of the human who invoked it. You'll design and ship the patterns - Cognito + IAM + scoped tokens - that make this real, deterministic, and auditable.
- Build the developer experience for internal agent builders: Templates, SDK helpers, deploy paths, observability, cost tracking. Make it so that every Hi Marley team can ship their own agent without reinventing security or hosting.
- Partner on security tooling with our Compliance & IT lead: Implement the scans, audits, MCP governance hooks, and DLP signals that the AI Security Ops role will use. You build the rails
- they build the gatekeeper.
- Identity & authorization fluency: You've built systems where authorization is the architecture, not bolted on. OAuth 2.1, scoped tokens, role inheritance, least-privilege design - these are second-nature to you.
- Partner on security tooling with our Compliance & IT lead: Implement the scans, audits, MCP governance hooks, and DLP signals that the AI Security Ops role will use. You build the rails; they build the gatekeeper.
- We build AI-powered software that keeps everyone in the claims conversation informed and connected.
- Own the hosting, deployment, and infra-as-code layer for every internal agent and tool we run.
Requirements
- Familiarity with Model Context Protocol or comparable agent-tool patterns.
Nice to have
- AgentCore, SageMaker, Workshop Studio.
- You can architect a multi-tenant platform on AWS without needing to outsource the hard parts.
- Bedrock, Cognito, IAM, EventBridge, Lambda, DynamoDB or Postgres, plus IaC (CDK or Terraform).
- Deep AWS expertise: You can architect a multi-tenant platform on AWS without needing to outsource the hard parts.
Benefits
- Bonus: AgentCore, SageMaker, Workshop Studio.
Company info
- You can present platform work to engineers, executives, and customers, and write docs people actually read.
- This role only succeeds if the rest of the company knows what's available.
- <li data-leveltext="" data-font="Symbol" data-listid="31" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":,"46977
- No third-party platforms - we are AWS-only by design.
- What We're Looking For:
- Hi Marley is on a mission to transform how the P&C industry communicates, making those moments faster, easier, and more empathetic for carriers and the customers they serve.
- As we continue to grow, we're looking for a Principal AI Platform Engineer to be a foundational hire on our new AI Operations team.
- You'll partner with the CTO and a UX-focused builder to make Hi Marley an AI-native company from the inside - and you'll do it on a strict AWS stack because our customers are insurance carriers who need real auditability, not a wrapper.
- Teamwork and shared enthusiasm are a core part of our culture, which is why this role involves joining us in the Boston office for 2-3 days each week.
Apply directly at Himarley →Create a free account for alerts like thisView Himarley immigration profile
This listing is sourced directly from Himarley's careers page and normalized into a canonical job model.