Join to apply for the Software Developer - Voice AI role at Tucuvi
Tucuvi is the global leader in clinical Conversational AI in healthcare. Our mission is to enable efficient and effective care for all, starting with AI‑led phone consultations that augment care teams' capacity. Our safe and medical‑grade AI autonomously conducts low‑risk clinical calls, inbound and outbound, streamlining caseload, augmenting patient reach, and improving patient outcomes. In Europe, our product, an AI Care management platform powered by an AI Clinical Agent named LOLA, is CE‑marked as a SaMD (Software as a Medical Device). Our enterprise‑grade technology is implemented in +50 care settings, improving tens of thousands of patients' lives in more than 40 different care pathways. We partner with leading healthcare systems to transform patient care and augment healthcare professionals’ capacities.
What You’ll Do
Your mission will be to design, develop, and scale robust AI‑driven systems that bring intelligence, automation, and reliability to our healthcare solutions. Your focus will sit at the intersection of backend engineering, Generative AI, and real‑time systems, building APIs, infrastructure, and pipelines that integrate AI capabilities into production with low latency and high reliability.
You’ll collaborate closely with AI engineers, backend developers, Product Managers, and leadership to ensure the solutions we deliver are reliable, scalable, observable, and clinically meaningful. Beyond coding, you’ll play a key role in evolving our GenAI architecture, making it efficient, maintainable, and ready to scale.
What To Expect During Your First Months With Us
* During your first month you’ll focus on shadowing key team members and getting up to speed with our product, AI systems, and workflows. You’ll familiarize yourself with our GenAI architecture, clinical use cases, and development processes.
* By the end of month three we expect you to start contributing independently to the design, development, and deployment of key AI systems. You’ll take ownership of projects, collaborate efficiently across teams, and begin making impactful improvements to our GenAI architecture.
* After six months you’ll be fully established in your role, proactively identifying areas for improvement, mentoring others, and driving critical projects forward. You’ll play a key role in shaping the future of our AI capabilities, ensuring our solutions remain scalable, efficient, and well aligned with clinical needs.
Responsibilities
* Design and develop scalable, low‑latency systems capable of handling high‑concurrency workloads in real‑time voice or multimodal scenarios.
* Develop and maintain APIs and services that integrate LLMs and AI features into production environments.
* Contribute to our internal AI serving strategy, helping us adopt open‑source model‑serving and MLOps tools.
* Architect and maintain cloud‑native backends (GCP) integrating Pub/Sub, Cloud Run, Firestore, and monitoring/alerting tools (Prometheus, Grafana, OpenTelemetry).
* Build and optimize ETL and streaming pipelines, ensuring data consistency, observability, and compliance.
With Whom You Will Work
* Andrés Torres, Director of Engineering
* Manuel Morillo, AI Software Engineer
* Tarek‑Asis Hamed, AI Software Engineer
* Iago Bermúdez, Frontend Developer
Requirements
* 3+ years of professional experience as a Software Engineer or AI Engineer, ideally in Conversational AI or real‑time systems.
* Proven experience deploying and maintaining AI or LLM‑based features in production, with a strong focus on scalability, low latency, and observability.
* Strong Python skills, including async programming, clean architectures (Hexagonal, DDD), and testing (Pytest).
* Solid understanding of real‑time pipelines and low‑latency architectures, ideally involving streaming voice or multimodal interaction (LiveKit, WebRTC, etc.).
* Expertise with Google Cloud Platform (GCP) and monitoring/alerting tools (Prometheus, Grafana, OpenTelemetry).
* Hands‑on experience with containerized environments (Docker, Kubernetes) and GitLab CI/CD for automated testing and deployments.
* Familiarity with Speech‑to‑Text (STT) and Text‑to‑Speech (TTS) engines (Whisper, Deepgram, Google Speech, ElevenLabs).
* Fluent in Spanish and English, both written and spoken.
Bonus
* Experience in MLOps (e.g. MLflow, Vertex AI, Weights & Biases) for model tracking, versioning, and retraining pipelines.
* Background in healthcare AI or regulated environments.
What We Offer
* 💰 Fixed and variable salary with flexible benefits through Cobee (ticket restaurant, transport, nursery, etc.).
* 🌍 Remote work in an async environment.
* 🕓 Flexible working hours.
* 💃 Teambuildings three times per year.
* 🏖️ 23 days per year + your birthday + 6 local and regional holidays added to your calendar (so you can choose when to enjoy them).
* 🧑🏫 Budget for training and personal development.
* 💻 A laptop (Mac) and the equipment you need (screen, etc.).
* 🛫 The possibility to join a team of good and ambitious people where you can create a real impact on people's lives.
Wanna know more? ⁉️ Are you interested in the position but you don’t meet all the requirements? ⁉️ Get in touch with us:
Sofia Nikolaeva
People & Culture Associate
#J-18808-Ljbffr