About the Role
Title: Sr. Backend Engineer
Function: Engineering
Reporting: VP of AI Product
Location: San Francisco, CA (Hybrid)
We are building the runtime that powers AI agents across our enterprise communication platform: a multi-tenant execution sandbox, a durable orchestration backbone, and the SDKs and tools agents run on. We want builders, not just users: engineers who have stood up an agentic framework end to end, from the ground up, rather than wiring together someone else's. You will own major subsystems and help set technical direction.
What you'll do
- A multi-tenant execution sandbox for agents with strict, provable data isolation.
- The durable execution backbone on Temporal, so long-running agents survive failures, restarts, and retries.
- The agent harness and SDKs: tool-calling, context, model orchestration, and the eval and guardrail loops that keep behavior safe.
- MCP tool exposure and external runtime interop.
- Observability and audit infrastructure for agent execution.
- The failure model: error handling, resource limits, and graceful degradation.
Skills and Qualifications
- Built an agentic framework or runtime end-to-end, from the ground up, not just used one. You have designed the agent loop yourself: tool-calling, context management, multi-agent orchestration, eval and guardrail loops, and the failure modes specific to agents. You can speak to the trade-offs you made and what you would do differently.
- 6+ years building backend systems or distributed infrastructure at scale.
- Built SDKs or platforms that other engineers build on top of.
- Production use of AI-assisted dev tools (Claude Code, Codex, Gemini CLI, or similar) across the full lifecycle: spec, build, review, and deploy validation.
- Multi-tenant design with hard tenant isolation, ideally in a regulated space (financial services, healthcare).
- Async and concurrent execution patterns (goroutines, async/await, thread pools).
- Secure API design with authn/auth at the service boundary.
- Observability and instrumentation: logging, tracing, audit trails.
Preferred Skills and Qualifications
- Workflow orchestration (Temporal, Airflow, Prefect), especially agentic workflows in production.
- Managed agent runtimes (Claude Managed Agents, Bedrock Agents, Google Agent Builder, Azure AI Services).
- Runtime isolation and sandboxing.
- Deep familiarity with agent dev kits (Google ADK, Claude Agent SDK, OpenAI SDK, LangChain, CrewAI, AutoGen) at the level of their internals, not just their APIs.
- MCP or similar tool and extension systems.
- gRPC or modern RPC.
- Multi-provider key management; secrets and credential rotation.
- Event-driven architecture (streaming, queues, event sourcing; Kafka or similar).
- Knowledge graphs for grounding agents (Neo4j, or Obsidian-style linked stores).
- Audit and compliance in regulated industries (PCI-DSS, SOC 2).
- Enterprise communication or messaging platforms.
Tech Stack
- Languages (fluent in two): Go, Python, TypeScript/Node.js, Rust.
- Infra: Kubernetes, CI/CD, OpenTelemetry / Prometheus / Grafana, SQL / document/graph stores.
- Security: threat modeling, secrets and rotation, audit trail design, data classification, and encryption.
What you'll get
- Great flexible healthcare plans from day one
- Access to voluntary benefits, including FSA/ HSA
- Supplemental Insurance
- 401k Employer Match
- Unlimited PTO in a company that respects your time
- Collaboration with driven, creative people from around the world
- Opportunity to be at the forefront of tech innovation.
- A fiercely inclusive, unapologetically diverse environment
