Intermediate/Senior Product Engineer

Symend•,

About The Position

We’re building a voice agent that calls people who are past due on bills, explains their situation, and negotiates a payment arrangement – in real time, without a human on the line. It uses synthetic voice, behavioral science, and LLM-orchestrated decision logic to run conversations that actually work. This role exists at the intersection of product and engineering, and it leans hard into both. 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’re not a PM who hands off to engineering. You’re not an engineer who gets handed a spec. You do both, and you’re accountable for whether the product finds its market. 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. The domain matters. You’re building AI that makes real-time decisions with real financial consequences – inside compliance guardrails, with a person on the other end of the line. Candidates who have worked in regulated, high-stakes AI application domains will have a meaningful head start. If you’ve survived a client integration that went sideways at 11pm and have opinions about when to throw out what the model generated, read on.

Requirements

Minimum 3 years experience building SaaS products at scale
LLM orchestration depth: built real agentic pipelines, understand context window constraints, tool call patterns, failure modes, and what happens when an agent loses the thread mid-call.
Voice AI and telephony familiarity: Hands-on experience with at least one of: Twilio, ElevenLabs, Retell, or Deepgram. Understand why real-time audio is technically hard – latency, media streaming, session state – and have built something that had to work under those constraints.
Full-stack implementation capability: write async Python with confidence (asyncio, FastAPI, SQLAlchemy async). Be comfortable in TypeScript/React and work across the frontend.
Client-facing discovery skills: run a conversation that surfaces the real problem, not just the stated one. Translate a messy client requirement into a scoped technical approach and explain it back to a non-technical stakeholder.
Integration and event-driven architecture: wire up external APIs, deal with inconsistent documentation, rate limits, and auth schemes, and make it reliable. Build webhook receivers, implement HMAC signature validation, handle replay attacks, and design for idempotency. Use Redis for pub/sub, streams, session state at scale.
AI tooling philosophy: use AI as a drafting partner, not a decision-maker. Reach for it on boilerplate, test scaffolding, and exploration. Own the design and know when the output needs to be thrown out.
Multi-tenant systems experience: build multi-tenant SaaS where tenant data bleed is a real threat, and describe specifically how you prevented it.
Cloud deployment literacy: ship to cloud-hosted containers. 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.
Agentic SDLC toolkit fluency: become an expert in a custom agentic development toolkit on top of Claude Code and internal tooling, understanding its capabilities and limitations.
Experience in regulated, high-stakes AI application domains is a plus.
Experience with client integrations that went sideways and opinions on when to discard model-generated output.
Experience with async Python (asyncio, FastAPI, SQLAlchemy async).
Experience with TypeScript/React.
Experience with Twilio, ElevenLabs, Retell, or Deepgram.
Experience with webhook receivers, HMAC signature validation, replay attack handling, and idempotency design.
Experience with Redis for pub/sub, streams, and session state at scale.
Experience shipping to cloud-hosted containers.
Experience reading GitHub Actions workflows and debugging deployments.
Experience with AI Coding Agents (Claude Code, Codex, OpenCode, etc.).
You do not need detailed tickets and a tech lead to make forward progress.
You can explain the failure mode at the API boundary.
You have built production agentic pipelines.
You are willing to be in client conversations.
You do not treat AI-generated code as ground truth.

Nice To Haves

B2B experience is an asset.
Azure experience is a plus.

Responsibilities

LLM orchestration depth: build real agentic pipelines, understand context window constraints, tool call patterns, failure modes, and what happens when an agent loses the thread mid-call.
Voice AI and telephony familiarity: Hands-on experience with at least one of: Twilio, ElevenLabs, Retell, or Deepgram. Understand why real-time audio is technically hard – latency, media streaming, session state – and have built something that had to work under those constraints.
Full-stack implementation capability: write async Python with confidence (asyncio, FastAPI, SQLAlchemy async). Be comfortable in TypeScript/React and work across the frontend.
Client-facing discovery skills: run a conversation that surfaces the real problem, not just the stated one. Translate a messy client requirement into a scoped technical approach and explain it back to a non-technical stakeholder.
Integration and event-driven architecture: wire up external APIs, deal with inconsistent documentation, rate limits, and auth schemes, and make it reliable. Build webhook receivers, implement HMAC signature validation, handle replay attacks, and design for idempotency. Use Redis for pub/sub, streams, session state at scale.
AI tooling philosophy: use AI as a drafting partner, not a decision-maker. Reach for it on boilerplate, test scaffolding, and exploration. Own the design and know when the output needs to be thrown out.
Multi-tenant systems experience: build multi-tenant SaaS where tenant data bleed is a real threat, and describe specifically how you prevented it.
Cloud deployment literacy: ship to cloud-hosted containers. 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.
Agentic SDLC toolkit fluency: become an expert in a custom agentic development toolkit on top of Claude Code and internal tooling, understanding its capabilities and limitations.
Lead a small delivery team of one to two junior and intermediate engineers.
Conduct pre-sales conversations to help clients understand possibilities.
Perform discovery to find the real job-to-be-done.
Implement and ship the product.
Feed learnings back into the core platform roadmap.
Lead at least one discovery conversation independently within 90 days.
Have three to four clients live on the voice AI product within 12 months.
Establish a repeatable delivery motion that is documented and transferable within 12 months.
Feed clear PMF signal back into the core roadmap within 12 months.