Product Engineer (TypeScript)

Vocca; Paris; Hybrid; EUR 70,000 - 120,000; Full time

Benefits offered by this job

BSPCE

Hybrid work 3 days at the office

Paris office

Claude Max provided

Job summary

Vocca is an AI voice agent startup in Paris building an automation platform for medical centres to handle calls, bookings and patient interactions. The product enables clinics to automate routine tasks while human staff focus on care.

The team emphasizes speed, quality, and data-driven decisions in a fast-growing healthcare tech market. As a senior full-stack engineer in a hybrid Paris office, you will own features end-to-end, collaborate across product, ops and sales, and help scale the

Qualifications

• 3 to 8 years building full-stack products in production.
• Strong TypeScript skills and code quality focus.
• Experience with scalable system design and frontend/backend integration.
• Ability to ship end-to-end features from spec to production.

Responsibilities

• Own features end to end from spec to production.
• Collaborate with ops, sales, and design for scalable onboarding.
• Contribute to frontend and backend development and code reviews.
• Follow design system and ship iteratively.

Skills

TypeScript

Full-stack development

Frontend engineering

Backend engineering

System design

Product thinking

Tools

Node.js

PostgreSQL

Design system

CI/CD

Job description

Our team shared’s mission is deploy AI agents to transform how patients and doctors connect

We believe healthcare shouldn’t be defined by missed calls, endless waiting lines, and overwhelmed staff. Patients and professionals deserve better.

Vocca builds AI voice agents that answer every call instantly, schedule and reschedule appointments, and free up staff to focus on what matters most: care.

Already trusted by 15 000+ providers, we’re transforming the patient–provider relationship, one call at a time.

Want to shape the future of healthcare?

• Discover our company culture and values

• Here is a product teaser

• Eliott's interview for Welcome to the jungle

• Eliott's quick interview for Speedinvest

• Articles on our A round (techfundingnews, Maddyness, les echos, our blog)

Vocca in a few words

Vocca is an AI voice agent that answers 100% of the calls of medical centres. The patient calls, the AI books the appointment or answers the question, and the medical secretaries keep their time for the cases where a human is really needed.

• $20M raised, with the founders of Alan and Datadog as investors

• Close to 1 million calls a month going through the platform

• More than 1,000 medical staff use our product all day

The problem

Every medical centre has its own rules. Who can book what, with which practitioner, at what time, what to do with an urgent case at 6 pm. Today these rules live in prompts and in the heads of our ops team. Each new clinic takes hours of manual work, and the ops team is the bottleneck of our growth.

We are building the platform that removes that bottleneck. A scenario engine where the behaviour of the agent is structured configuration, not free text. A self-serve onboarding where a clinic connects its software and sets itself up. A dashboard where the medical staff stop executing and start supervising: the agent handles the volume, humans check what matters.

This is the difference between selling a service and selling a product. The long term vision is simple: a clinic signs, connects its software and is live within days, without a single developer involved. You would be building that.

What you will own

• The scenario engine and its configuration model. One product that handles the rules of thousands of medical centres without becoming a swamp.

• The self-serve onboarding, from the backend to the dashboard. Internal tooling already took a clinic deployment from days to under an hour. The next step is zero developer ticket on a standard onboarding.

• The dashboard our clinics use all day. Fast, reliable and clean enough that a medical secretary prefers it to the phone. We take frontend quality seriously and follow a design system written in code.

• Your features, end to end. From the spec with the ops team to production, and the fix when something breaks, with the reason it does not happen again.

How we build

• Experimental, not R&D. You test, you prove with data, you ship. Challenging a decision means coming back with a result, not a debate.

• Ship, then fix the last 1%. We ship the version that works, then fix the last 1% when it shows up. With AI, this trade off is much cheaper than before. The judgment about what not to touch is yours.

• AI, seriously. Agents in every workflow, Claude Max provided. A migration estimated at 3 months was done in 2 weeks.

• Close to the field. Every change lands in front of more than 1,000 medical staff. You talk every day with the ops team that deploys clinics and the sales team that sells the product.

Stack

TypeScript everywhere, backend and frontend (Node, monorepo), PostgreSQL, a design system written in code. We are migrating our last Python services to TypeScript over the coming months.

Who does well here

• 3 to 8 years building full-stack products in production, in startups that were growing fast.

• You stayed long enough somewhere to see a system live, break and get better, and you learned from it.

• TypeScript is your main language, backend and frontend, not a line on your CV. You have a real eye for interface quality and the discipline to follow a design system.

• You think about the product and the business as much as the code, and you know how to build systems that hold when the volume explodes.

• You move without waiting for a perfect frame: you try, you propose, you ship. You ask for help when you are stuck.

• You had good practices before AI: solid system design, clean refactoring and a good nose for the risks of generated code that nobody tested.

Probably not for you if you need every feature fully specified before you start

What we expect from you

• First week. Onboarded on the stack, your first improvement on the dashboard is in production.

• First month. You own one feature end to end, from the spec with the ops team to production, without mockups or hand-holding.

• First 3 months. The first version of the scenario engine is in production. A standard clinic can be onboarded without a developer ticket.

• 6 to 12 months. Most new clinics are live within 7 days. Clinics configure their own rules in the dashboard.

Process: 4 steps, fast

1. 45 min with Nans (Talent).

2. 45 min with Pierrick, Head of Engineering.

3. 1h30 in our office with the engineering team: coding without AI and a real conversation about product architecture.

4. 30 min with Hugo, CTO.

Then references and an offer. When the match is obvious, we have made an offer in 24 hours. You get feedback at every step.

Practical

• Paris, rue d'Alexandrie (Sentier), new offices.

• Hybrid, 3 days at the office.

• BSPCE.

• Claude Max provided.

We aim to keep the process within 30 days. You’ll receive continuous feedback throughout.

Why should you join Vocca?

• An entrepreneurial adventure, with a supportive, high-energy, execution-focused team

• A product already live, with delighted customers in a fast-growing market (healthcare automation, voice AI)

• A true scaling phase, with everything still to build

• Real responsibilities from day one

We hire people, not roles.

If you're excited about our opportunities but don't check every box, we'd love to hear from you. Everyone, no matter how underrepresented, should feel free to apply as it can only bring learnings or success. If you identify yourself as a woman: Did you know that research shows women often apply only when meeting 100% of requirements?

We'll be thrilled to receive your application!