Salary / Hourly Rate: $100,000 - $200,000 per year
Benefits: Open to considering relocation for the right candidate but really prefer local candidates,Candidates should already be based in US
Role Information
Role Overview: N/A
Responsibilities: Create the collective memory: ingest and unify multi-source data into a multi-level context graph with strong tenant isolation., Orchestrate agentic systems: design planner/executor patterns, tools, and policies (including MCP-style interfaces) that turn context into content and then into actions; define simple eval harnesses., Deliver where users work: expose capabilities through native surfaces (apps, chat, integrations) to reduce context switches and meta-work., Prove outcomes: define success metrics (tasks auto-completed, adoption/retention, pipeline lift) and wire observability so we can ship → learn → iterate quickly while meeting latency targets., Balance cost and reliability: tune accuracy, latency, and run cost for retrieval and agents; implement fallbacks and safeguards for real-world load., Raise the bar: write RFCs, lead design reviews, mentor peers, and improve code quality, SLOs, and on-call practices.
Qualifications: 4+ years building and owning backend or platform systems end-to-end with measurable business impact., Strong Python; able to stand up cloud infrastructure and production services on AWS., Experience stitching messy, multi-source data into models a product can reason over; strong privacy, reliability, and multi-tenant instincts., Comfortable deciding with ~70% information, instrumenting what matters, and iterating., Nice to have: exposure to agent orchestration/planning, retrieval or graph-shaped context, eval frameworks, and distributed systems at scale.
Minimum Requirements: 4+ years building and owning backend/platform systems end-to-end,Has not applied to the company before,Hybrid availability: able to work 3 days per week in San Francisco, New York City, or Vancouver (or relocating on an agreed timeline)
Screening Questions: Walk me through a 0→1 platform or data system you owned end-to-end. What were the trade-offs, and how did you instrument outcomes?,Work authorization (KO): Do you currently have work authorization for that location (US or Canada) without sponsorship?,Describe a planner/executor loop you implemented. How did you evaluate quality and add fallbacks?,Give an example where you reduced latency or run cost by 30%+ without hurting quality. What changed?
Company Information
About Company: N/A
Culture: N/A
Additional Information
Interview Process: 2-3 interviews and technical assessment with the team + founders. Initial screening by VP of Engineering.
Day to day: Days 0–30: Stand up ingestion paths, define the context-graph MVP, wire observability + eval harness, and ship one end-to-end agent flow to a pilot user., Days 31–60: Harden multi-tenant boundaries, expand planner/executor tools & policies, add 1–2 key integrations (e.g., CRM, sales tools), and review metrics weekly with Product/Sales., Days 61–90: Tune latency/cost and add fallbacks, document runbooks, establish basic SLAs/on-call for agent pipelines, and iterate based on adoption and task-completion data.
Team: Report directly to the founders (CEO/eng lead) on a small, senior, high-ownership team. You’ll partner daily with Product and closely with Sales/RevOps, with decision-making authority over architecture, tooling, and shipping priorities; cadence includes a daily stand-up and a weekly design/growth review. Work alongside a small, senior, high-ownership founding team reporting directly to the Founders (CEO/Eng lead).
Growth: Meaningful equity and the ability to shape platform architecture from day one. Clear paths to Principal Engineer or Founding Staff scope, with opportunities to mentor, influence hiring, and set standards for reliability, security, and developer velocity.
Ideal Candidate Profile: Staff-level IC from an AI/data/infra or GTM tooling company who has owned a platform surface from 0→1 and through reliability hardening, Strong Python + AWS; comfortable with Postgres or DynamoDB, FastAPI/GraphQL, Kubernetes, Pulumi, event-driven design, Experience with agent orchestration, retrieval, or graph-shaped context; adds evals and observability to ship quickly and safely, Excellent instincts for multi-tenant isolation, privacy, reliability, and cost control, Communicates trade-offs clearly; collaborates well with Product and GTM, Hybrid 3 days per week in SF, NYC, or Vancouver
