Docplanner is looking for an AI/LLM Engineer to drive the advancement of our conversational AI capabilities. You'll focus on prompt engineering, multi-agent orchestration, automated testing, and deploying LLM integrations in production, working closely with Backend Engineers to deliver AI experiences.

What You'll Do

Design, optimize, and version prompts for production voice and chat LLM applications.
Architect and orchestrate multi-agent systems for complex conversations.
Build automated testing and validation frameworks for LLM outputs.
Implement prompt versioning, storage, and retrieval systems.
Collaborate with Backend Engineers to deploy and scale LLM-based systems.
Integrate LLMs with communication APIs such as Twilio, WhatsApp, and ElevenLabs.
Implement RAG solutions and vector search for multilingual environments.
Monitor performance metrics and conversation quality.
Research and prototype multi-agent frameworks, both open-source and commercial.
Experiment with conversational AI and real-time speech processing techniques.
Contribute to evolving the team's LLMOps best practices.
Continuously improve conversational quality, RAG pipelines, and reduce latency.

What We're Looking For

2+ years of hands-on experience with LLMs, such as OpenAI or open-source models.
Strong knowledge in prompt engineering and LLM optimization strategies.
Experience evaluating LLMs, designing evaluation frameworks, creating test datasets, and defining success metrics.
Familiarity with automated testing pipelines and CI/CD-integrated evaluation systems.
Experience in multi-agent architecture, from design to development of orchestration for complex LLM systems.
Good understanding of transformer architectures and proficiency in LLM frameworks like LangChain or LlamaIndex.
Proficiency in Python.
Experience with RAG pipelines and vector databases.
Experience in cross-functional teams, ability to work in fast-moving environments where you own outcomes, not just tasks. Comfortable with ambiguity.

Nice to Have

Experience in healthcare industries.
LLM integration with voice platforms like Twilio and ElevenLabs.
Background in conversational AI, chatbots, or voice assistants.
Knowledge of real-time speech processing and multi-modal systems.
Familiarity with functional programming principles and advanced NLP.
Exposure to OOP stacks like .NET or PHP.
Understanding of security and privacy in conversational AI.

Technical Stack

Languages: Python
Frameworks: LLM frameworks (LangChain, LlamaIndex)
APIs & Services: Twilio, WhatsApp API, ElevenLabs
Data: Vector databases

Team & Environment

You will be part of the Tech & Product team at Docplanner.

Benefits & Compensation

100% remote work, with the option to join offices in Bologna or Barcelona.
One extra day off for your birthday.
Access to iFeel, our mental wellbeing platform.
For Italy: €8/day meal vouchers and private health coverage via Metasalute.
For Spain: Comprehensive private health insurance with Adeslas, Flexoh flexible compensation platform, Wellhub gym & wellness network membership, and Language courses.