Senior AI Engineer (Python / Real-Time Systems)

Location: Remote (EU time zones preferred)
Engagement: Full-time, long-term

About the Project

Our client is a European health technology company building an AI-driven virtual assistant for clinicians - a real-time system that helps healthcare professionals perform tasks faster and more accurately.

Their mission is to create intelligent, low-latency AI agents that can communicate naturally with humans through text and voice, supporting healthcare providers, payers, and pharmaceutical companies.

Stack: Python, FastAPI, Docker, Kubernetes, Argo CD, gRPC, Redis, Postgres, WebRTC
Focus: Real-time multi-agent AI, event-driven architectures, voice AI systems

About the Candidate

The ideal candidate is a Software-First AI Engineer - someone who can design, build, and optimize production AI systems, not just prototype them.

You’ll be responsible for developing real-time AI agent infrastructure, improving low-latency performance, and ensuring high reliability in non-deterministic environments.

You’ll work closely with the Head of AI and Engineering leads to architect and ship critical components of the platform.

You Will

• Own and evolve the core “brain” service powering multi-agent AI systems.
• Design and build low-latency pipelines for streaming text and voice communication (WebRTC, SIP).
• Develop and optimize event-driven AI architectures for real-time inference.
• Implement evaluation pipelines to monitor model performance, faithfulness, and reliability.
• Integrate and orchestrate LLM-based agents (planner–executor–critic patterns, shared memory, role routing).
• Contribute to ongoing system re-architecture for scalability and latency improvements.
• Collaborate cross-functionally with AI, backend, and product teams to ship quickly and reliably.

You Are

• A practical engineer with a strong Python background and proven experience building real-time systems.
• Curious, fast-moving, and comfortable working in non-deterministic environments (AI agents, LLMs).
• Independent, ownership-driven, and able to prioritize effectively in a startup setting.
• Communicative, fluent in English, and proactive in collaboration.

Preferred Experience

• 5+ years in software or AI engineering, with a strong Python foundation (FastAPI, asyncio, pydantic).
• Experience with real-time systems (WebRTC, LiveKit, SIP, or similar low-latency streaming tech).
• Understanding of LLM architecture, evaluation frameworks, and multi-agent orchestration patterns.
• Hands-on work with RAG pipelines, event-driven design, and asynchronous communication.
• Exposure to Docker, Kubernetes, and modern CI/CD practices.
• Bonus: Experience in voice AI, healthcare data, or evaluation tooling (e.g. DeepEval, DSPy).

Responsibilities

• Build and maintain AI agent systems optimized for sub-second latency.
• Implement programmatic prompt evaluation and automated performance checks.
• Instrument observability (structured logs, metrics, OTEL).
• Collaborate on infrastructure decisions and architectural design.
• Ensure system scalability, fault tolerance, and reliability.

Working Practices

• Fully remote (EU time zones preferred).
• Direct collaboration with technical leadership (Head of AI, Head of Engineering).
• Fast iteration and continuous feedback.
• Opportunity for long-term growth and influence on core architecture decisions.

Cooperation Details

• Engagement: Full-time, long-term
• Language: English
• Timezone: Europe-based or similar overlap