Key skills
TypeScriptPythonGoAILLMOpenAILangChainVector DatabasePineconeNode.jsAWSGCPGoogle CloudTerraformServerlessLambdaIAMCloud FunctionsPub/SubAuth0OktaCI/CD
About this role
Facet is a financial advisory firm founded in 2016, aiming to provide objective, personalized financial advice through a combination of human expertise and cutting-edge technology. The AI Platform & Operations Engineer will design and maintain the infrastructure for AI features, optimize serverless architectures, and implement automated security measures to support the company's growth.
Responsibilities:
- Design and maintain the infrastructure required to power AI features, including vector database management, model deployment pipelines, and secure integration with LLM providers
- Build and evolve our Internal Platforms, focusing on self-service, automation, and reducing cognitive load for internal teams
- Optimize and secure our 100% cloud-native environment, developing and deploying scalable serverless and event-driven architectures (AWS Lambda, Google Cloud Functions, EventBridge, Pub/Sub)
- Implement automated security guardrails within the CI/CD pipeline
- Lead the 'Identity/IAM Architecture' to ensure least-privilege access and build automated compliance checks into our Infrastructure-as-Code (Terraform)
- Develop and enforce technical guardrails for our internal AI platform to manage data privacy, cost controls, and ethical usage monitoring
- Drive a 'manual-is-a-bug' culture by automating environment provisioning, incident response, and performance monitoring
Requirements:
- 4-8 years of experience in a Platform, DevOps, or Site Reliability Engineering role
- Deep experience with AWS and/or GCP, specifically focused on serverless architectures
- Expert-level proficiency with Terraform and a 'policy-as-code' mindset
- Practical experience designing IAM architectures and implementing automated security scanning/compliance in CI/CD
- Proficiency in at least one modern language (Python, Go, or TypeScript/Node.js) to build custom tooling and integrations
- Experience supporting production AI workflows (e.g., Pinecone, LangChain, OpenAI API integrations)
- Familiarity with modern AuthN/AuthZ protocols and providers (e.g., Okta, Auth0, AWS IAM Identity Center)
- Experience building or maintaining high-scale event buses and asynchronous messaging systems
- Experience treating 'The Platform' as a product, with a focus on improving the Developer Experience (DX)