Senior Full Stack Software Engineer, Backend - AI products

The Opportunity

We're at an exciting point: agentic automation is moving from prototype to production, and we need a senior engineer who can own high-impact work end-to-end. You'll turn ambiguous goals into shippable milestones, operate what you build in production, and iterate fast based on real customer feedback — all in a team that moves quickly without sacrificing reliability.

What You'll Do

• Take primary ownership of a major capability (e.g., outbound/inbound concierge workflows, clinical assistant experiences, or a core LLM/voice platform subsystem) within your first 90 days
• Ship hardening improvements into production — monitoring/alerts, runbooks, safer rollout strategies, and top error/latency reductions
• Improve our LLM and voice agent workflows through durable architecture changes: tool boundaries, guardrails, and eval-driven iteration
• Turn ambiguous asks into shippable milestones with clear communication and tight iteration loops — reduce 'stuck' work for the team
• Help the team scale delivery without losing speed by establishing better patterns, defaults, and maintainability standards
• Raise the bar on operational maturity: incident follow-through, observability, and reliability
• Contribute to security and compliance maturity through secure-by-default practices and sound judgment

About You

Must-have:

• Strong backend engineering fundamentals: TypeScript/Node services, API design, data modelling
• Practical full-stack fluency — comfortable contributing in React/FE when needed, not a specialist
• Hands-on experience integrating with LLMs or agent frameworks and building production workflows around them (evaluation, observability, safety)
• Comfort operating production systems: debugging, incident response, monitoring, and follow-through
• A track record of owning projects end-to-end — scope → design → build → ship → monitor → iterate
• Strong written and verbal communication; able to join customer calls, debug issues from real workflows, and translate feedback into clear engineering plans

Nice-to-have:

• Experience building voice agent workflows (call flows, state management, reliability patterns) and integrating with vendors like Retell
• Experience with speech-to-text workflows and vendors like Deepgram
• Security/compliance-adjacent experience: threat modelling mindset, secure defaults, safe data handling
• Front-end test automation and/or build/deploy automation experience
• AWS/GCP and production operations experience
• Comfortable using AI dev tools day-to-day (Claude/Claude Code, Gemini, CodeRabbit, LangSmith, etc.) while maintaining quality and safety

Success in This Role Looks Like

30 days: You've taken ownership of a major capability, shipped your first production improvement, and have a clear picture of where the biggest gaps are

60 days: You're iterating autonomously — turning ambiguous asks into milestones, closing incident/feedback loops, and improving observability across the stack

90 days: A production capability is noticeably more reliable and maintainable because of your work; the team is moving faster as a result

Long-term: You're setting the engineering bar — better patterns, tighter operational discipline, and a system that scales without needing heroics