AI Backend Engineer (Python, Agentic AI)

IT Craft is looking for an experienced AI Backend Engineer to join the development of a digital wellness product. The solution uses AI to process health, nutrition, fitness, and wearable data and provide personalized insights, recommendations, and user journeys. The product includes voice-based conversational functionality, an agent-based architecture, long-term memory, behavioral profiling, data personalization, and integrations with external data sources. The engineer will take end-to-end ownership of the AI backend, from architecture and implementation to production setup, monitoring, and ongoing improvement. 

Key Responsibilities:

• Design and evolve production AI architecture covering agent orchestration, routing, tool calling, RAG, memory and structured outputs;
• Select and integrate LLM, speech (STT/TTS) and vision models from different providers, balancing quality, latency, cost and EU data residency;
• Define the data architecture for conversational, nutrition and wearable data to support personalization and a digital twin;
• Translate product requirements into technical solutions and document key architecture decisions together with product owners;
• Develop and extend the Python-based AI backend, including voice pipelines with real-time latency requirements;
• Set up cloud infrastructure, containers, vector stores and model gateways using infrastructure-as-code in collaboration with the DevOps/CI-CD engineer;
• Build integrations for wearable APIs, food databases and image-recognition services;
• Implement user memory and personalization, including adaptation to communication style;
• Set up LLM observability for tracing, token and cost tracking, latency, error rates and alerting;
• Build automated evaluation and regression processes for prompts and agents, including offline evaluations, LLM-as-a-judge and human review;
• Implement guardrails and safety mechanisms for health-related conversations, including escalation logic and hallucination controls;
• Monitor model and prompt performance in production and continuously improve models, prompts and agent behavior;
• Ensure GDPR-compliant handling of sensitive health data (special category data), including EU hosting, encryption, access control, data minimization and deletion;
• Keep the architecture prepared for EU AI Act requirements and the wellness/medical-device boundary (MDR);
• Build the data foundation for personalization, experimentation and future predictive models.

Required Skills:

• 6+ years of experience in software or ML engineering, with at least 2 years of hands-on experience building and running LLM-based systems in production;
• Strong proficiency in Python, with solid SQL and data modeling skills;
• Hands-on experience designing and implementing agentic systems using orchestration frameworks such as LangGraph or similar, including tool calling, structured outputs, RAG, and long-term memory;
• Experience working with multiple LLM providers and model gateways, as well as prompt engineering and context engineering at scale;
• Practical LLMOps experience covering evaluation frameworks, observability, and optimization of cost and latency;
• Experience with Docker, Kubernetes or managed container services, infrastructure-as-code, and CI/CD;
• Good understanding of security and data protection requirements when working with sensitive personal data;
• Ability to independently own architecture decisions and collaborate effectively with product and engineering teams;
• Strong written and spoken English (Upper-Intermediate+ / Advanced).

Nice to have:

• Experience with real-time voice AI, including streaming STT/TTS, speech-to-speech models, and latency optimization;
• Experience working with health, fitness, or wearable data, including time-series data and APIs such as HealthKit / Health Connect;
• Experience with personalization, recommendation systems, A/B testing, and statistics;
• Experience with vision models for food recognition;
• Experience in regulated environments such as GDPR Art. 9, EU AI Act, MDR or ISO 27001.

IT Craft offers:

• Competitive compensation according to the qualifications.
• Flexible working hours, remote work;
• Opportunity for career growth;
• Reward for sport activities;
• In-house English training;
• A friendly team of open-minded people.

Please send your CV!

By submitting your application, you consent to the processing of your personal data in accordance with IT Craft's Privacy Policy, available at https://itechcraft.com/datenschutz/.