Note: The job is a remote job and is open to candidates in USA. Symend is building a voice agent that calls people who are past due on bills, explaining their situation and negotiating payment arrangements in real time. The role involves owning the full product lifecycle, leading a small delivery team, and ensuring the product meets market needs.
Responsibilities
- You’ll own the full lifecycle of that product: pre-sales conversations where you help a client understand what’s possible, discovery where you find the real job-to-be-done, and implementation where you build and ship it
- You’ll lead a small delivery team, one to two junior and intermediate engineers, operating on a parallel track to the core platform
- What you learn feeds back into the roadmap
- What you ship is the conversational product
- You’ve built real agentic pipelines
- You understand context window constraints, tool call patterns, failure modes, and what happens when an agent loses the thread mid-call
- You should be able to explain where your last pipeline broke and why
- Hands-on experience with at least one of: Twilio, ElevenLabs, Retell, or Deepgram
- You know why real-time audio is technically hard – latency, media streaming, session state – and you’ve built something that had to work under those constraints
- You write async Python with confidence: asyncio, FastAPI, SQLAlchemy async
- You’re comfortable in TypeScript/React and can work across the frontend, but you don’t need to be a specialist there
- You know how to run a conversation that surfaces the real problem, not just the stated one
- You can translate a messy client requirement into a scoped technical approach and explain it back to a non-technical stakeholder without losing the room
- You’ve wired up external APIs, dealt with inconsistent documentation, rate limits, and auth schemes, and made it reliable
- Webhooks are the primary integration pattern for Twilio, ElevenLabs, and Retell
- You’ve built webhook receivers, implemented HMAC signature validation, handled replay attacks, and designed for idempotency
- You’ve used Redis as more than a cache: pub/sub, streams, session state at scale
- You use AI as a drafting partner, not a decision-maker
- You reach for it on boilerplate, test scaffolding, and exploration
- You own the design
- You know when the output needs to be thrown out
- You’ve built multi-tenant SaaS where tenant data bleed is a real threat, not a hypothetical, and you can describe specifically how you prevented it
- Per-tenant credential scoping, namespaced keys, org-scoped access patterns are second nature
- You’ve shipped to cloud-hosted containers
- You can read a GitHub Actions workflow, understand why a build fails in CI but works locally, and debug a deployment without needing someone to translate the logs
- You’ll become expert in it
- Not just as a user, but as someone who understands its capabilities well enough to identify where it falls short and push it forward
Skills
- Minimum 3 years experience building SaaS products at scale
- LLM orchestration depth is the floor
- Voice AI and telephony familiarity
- Full-stack implementation capability
- Client-facing discovery skills
- Integration and event-driven architecture
- AI tooling philosophy
- Multi-tenant systems experience
- Cloud deployment literacy
- Agentic SDLC toolkit fluency
- B2B experience is an asset
Company Overview
Company H1B Sponsorship