Senior ML/AI Engineer

A European AI startup developing a next-generation intelligence platform for business decision-making, focusing on advanced reasoning systems, retrieval architectures, knowledge graphs, and AI agents to improve strategic decision-making.

• 5+ years of experience in ML Engineering, Applied AI, Search & Retrieval, or Backend AI Systems
• Strong Python development experience in production environments
• Hands-on experience with LLM-based systems, retrieval pipelines, embeddings, structured outputs, and agent orchestration
• Experience building evaluation frameworks, automated validation pipelines, golden datasets, or human feedback loops
• Understanding of retrieval failure modes such as hallucination amplification, ranking drift, stale context, and retrieval gaps
• Experience with Knowledge Graphs and graph-based memory systems (e.g., Neo4j)
• Experience building APIs, asynchronous services, and production-grade backend systems
• Knowledge of observability, monitoring, schema validation, and debugging distributed systems
• Strong focus on measurable quality improvements beyond proof-of-concept development
• Experience using AI-native development tools such as Claude Code, Codex, Cursor, Gemini or similar

Nice to have:

• Experience with model fine-tuning, distillation, or local model deployment
• Experience working with agentic systems and long-term memory architectures
• Knowledge of sovereignty-driven model strategies
• Practical experience with graph, vector, lexical, and hybrid retrieval techniques
• Experience building AI products used in production by enterprise customers

• Build scalable memory and retrieval systems for high-context AI workflows
• Design hybrid retrieval architectures combining vector search, knowledge graphs, lexical search, and structured data
• Develop evaluation frameworks to benchmark retrieval quality, memory performance, and reasoning effectiveness
• Build agent memory interfaces that enable AI systems to query, inspect, and reuse context
• Define and improve quality metrics such as recall, provenance, latency, reliability, and cost efficiency
• Implement routing mechanisms deciding when to use retrieval, reasoning, or agent-based workflows
• Develop fine-tuning, distillation, and model adaptation pipelines
• Build observability and monitoring solutions for AI workflows including retrieval failures, model regressions, and cost tracking
• Work closely with engineers and product leaders to continuously improve AI system quality and decision-making capabilities

Please be informed that the data controller is iTeamly (hereinafter "controller"). You have the right to request access to your personal data, their rectification, erasure or restriction of processing, the right to object to processing, as well as the right to data portability and to lodge a complaint to the supervisory authority. Personal data will be processed for the purpose of the recruitment process. Provision of data to the extent resulting from the Act of 26 June 1974 Labour Code is mandatory. In the remaining scope, providing data is voluntary. Refusal to provide mandatory data may result in the impossibility to carry out the recruitment process. The Administrator processes mandatory data on the basis of a legal obligation incumbent upon him/her, while with regard to additional data, the basis for processing is consent. Personal data will be processed until the recruitment procedure is completed and for the period of the possibility of asserting potential claims, and in the case of consent to participate in future recruitment procedures - until the withdrawal of such consent. Consent to the processing of personal data can be withdrawn at any time. The recipient of the data is the Just Join IT service and other entities to whom we have entrusted the processing of data in connection with recruitment.