Staff Backend Engineer (AI Platform Team)

About the role

Some of the things you’ll do:

• Own the long-term architecture for AI orchestration frameworks, agent-based workflows, and model lifecycle management.
• Lead cross-functional delivery of AI features from proof of concept to production rollout, coordinating engineering, product, design, and CX.
• Establish best practices for prompt engineering, evaluation, versioning, observability, and incident response for AI services.
• Design and optimize low-latency streaming pipelines for speech and other real-time data when the customer experience demands it.
• Drive continuous cost, performance, reliability, and security improvements for models and infrastructure.
• Mentor engineers through design reviews, code reviews, and technical coaching, raising the bar for excellence across teams.
• Partner with security and platform leaders to ensure data privacy, compliance, and operational excellence.
• Stay current on advances in LLMs, agent architectures, and emerging tooling, translating insights into actionable roadmap proposals.

Tech Stack & Tools:

• Our backend is built on Node using Typescript.
• Our AI Infrastructure uses temporal.io, vector DBs, libraries like Langchain and top-tier llm models.
• We use Kubernetes on AWS to orchestrate our infrastructure setup and deployment.
• The overall architecture is event-driven microservices with RabbitMQ at the center of it.
• We use a variety of databases for different purposes: Postgres, Mongo, Elastic, and Redis.
• We have the following clients - Web (React), Android and iOS.
• We use Kong as our public API Gateway.
• Observability Tools: Datadog
• Other Tools: Figma, Linear, Notion, and Slack

About you

• 10+ years of backend or platform engineering experience, including LLM-driven systems in production.
• Proven success leading architecture for business-critical services, balancing innovation with operational pragmatism.
• Deep knowledge of LLM integration patterns, prompt design, vector search, and agent frameworks.
• Expertise in event-driven and streaming architectures; you can reason about concurrency, ordering, and back-pressure under load.
• Track record of driving cost optimization, observability, and incident response for AI workloads.
• Excellent written and verbal communicator who aligns diverse stakeholders and produces clear, thorough design docs.
• Collaborative leader who mentors others, fosters psychological safety, and elevates the entire engineering organization.
• Comfortable with ambiguity, you break down complex problems, make informed trade-offs, and deliver iterative value quickly.
• Empathetic and customer-focused, you balance technical decisions with user experience and business impact.

Compensation

• SF Bay Area, Los Angeles, Seattle, Portland, Boston, New York, and Washington, DC Metro: $205,000-$242,000 USD
• All other US Locations: $185,000-$217,800 USD
• Canada: $189,000- $222,000 CAD

Who we are