Our client is a pioneering HealthTech scale-up developing a first-of-its-kind AI assistant designed by clinicians, for clinicians. They are tackling one of the most urgent global challenges: the critical shortage of healthcare professionals. By building a controllable and highly customizable 'AI brain,' they provide real-time, reliable support across the entire care continuum. This is a chance to work on a product where your code directly alleviates the burden on frontline medical staff.
Dé el siguiente paso en su carrera profesional ahora: desplácese hacia abajo para leer la descripción completa del puesto y envíe su solicitud.
As AI Engineer, you will own and evolve the core "brain" service of this company platform. This is not about building simple wrappers;
you will architect sophisticated multi-agent systems that reason and communicate in real-time via voice and text. You will tackle high-stakes challenges in low-latency streaming, autonomous orchestration, and continuous evaluation, shipping fast-moving Python services at the intersection of cutting-edge AI and human-centric health technology.
We can hire this position ideally in Spain or UK.
Main Responsibilities:
* Core Intelligence Ownership: Lead the end-to-end architecture and evolution of the "core brain" service, taking full responsibility for SLAs, latency budgets, and deployment strategies.
* Real-Time Voice & Text Systems: Design and operate low-latency communication systems featuring streaming voice/text, Voice Activity Detection (VAD), and complex interaction handling (barge-in, turn-taking, and interruptions).
* Advanced Multi-Agent Orchestration: Build sophisticated multi-agent systems using planner–executor–critic patterns, shared memory, and advanced coordination protocols.
* Reasoning Optimization: Implement and refine complex reasoning frameworks, including ReAct and Chain-of-Thought (CoT), as well as Tree/Graph-of-Thought architectures where applicable.
* Automated Prompt Engineering: Leverage programmatic optimization tools (such as DSPy, MiPRO, or GEPA) to compile and evolve prompts iteratively under strict evaluation constraints.
* High-Performance RAG Engineering: Develop robust Retrieval-Augmented Generation (RAG) pipelines focusing on high-signal retrieval, hybrid search, re-ranking, and query rewriting to ensure grounded and faithful AI responses.
* Observability & Continuous Evaluation: Architect a comprehensive evaluation framework—from pre-call safety checks to post-call automated evals (hallucination detection, red-teaming)—using OpenTelemetry and structured logging to monitor drift and performance in real-time.
* High-Velocity Backend Development: Ship high-quality, production-ready Python services using FastAPI, ensuring high performance and continuous integration/deployment (CI/CD) gates.
Requirements:
* Core Backend: Extensive experience with Python, FastAPI, Pydantic, and asyncio for high-performance service development.
* AI & Data: Proven track record with Multi-agent systems, Vector Stores, and advanced RAG architectures.
* Infrastructure: Proficiency in Docker, Kubernetes (K8s), and Terraform for scalable deployments.
* Real-Time Ops: Familiarity with STT/TTS (Speech-to-Text/Text-to-Speech) and monitoring via OpenTelemetry (OTEL).
Preferred Experience (Nice to Have)
* Real-Time Communication: Hands-on experience with WebRTC stacks, LiveKit, and SIP gateways .
* AI Evaluation: Deep dive into DeepEval or similar LLM-as-a-judge frameworks.
* Prompt Optimization: Experience using DSPy for automated prompt compilation and self-improving workflows.
What's on offer?
* Stability & Growth: Permanent contract with a long-term vision and deep investment in your professional journey.
* Impactful Work: Build cutting-edge, real-time agent technology within a best-in-class HealthTech team where your code has a direct impact on global healthcare.
* High-Octane Technical Environment: Join a highly motivating atmosphere that fosters continuous learning, peer-to-peer mentorship, and the freedom to experiment with the latest AI breakthroughs.
* Flexibility & Balance: Truly flexible work-life integration with Remote-first or Hybrid options in our Barcelona hub. For people living in another Spanish cities the position can be remote.
* Team Culture: Engaging team-building events and fun off-sites in Barcelona to connect with a diverse, international team.
* Premium Tools: High-tech laptop of your choice and a budget for solid dev ergonomics to ensure your workspace is optimized for peak performance.
* Continuous Learning: Access to the latest tools, research papers, and internal knowledge-sharing sessions on the frontier of Multi-agent systems and LLMs.
Our recruitment process? xqbhyrx
Step 1: Interview with one of our recruiters
Step 2: Technical Interview with Hiring Manager
Step 3: Interview with another member of the team
Step 4: Cultural Fit Interview
Hay opciones de teletrabajo/trabajo desde casa disponibles para este puesto.