Senior AI Engineer -- Agentic AI

Senior AI Engineer – Agentic AI Systems Location & RequirementsLocation: Budapest or Szeged onlyLanguage: Fluent English requiredNote: This position requires candidates to be locally based in HungaryAbout the RoleWe are looking for an innovative AI Engineer to architect and deploy cutting-edge agentic AI systems—autonomous, goal-driven agents that reason, plan, and execute complex tasks with minimal human oversight. You will work at the intersection of software engineering and advanced AI, building scalable multi-agent workflows that integrate seamlessly into enterprise ecosystems.This is an opportunity to shape the future of autonomous AI systems, working with state-of-the-art LLMs and orchestration frameworks to solve real-world business challenges.What You'll DoArchitect Agentic AI SystemsDesign and build multi-agent frameworks leveraging patternsDevelop autonomous reasoning modules powered by advanced LLMs (GPT-4/5, Claude, Falcon)Create goal-directed agents capable of dynamic decision-making and self-correctionEngineer Context & Memory SystemsImplement sophisticated context management strategies including dynamic injection, retrieval-augmented generation (RAG), and long-term memory architecturesBuild safety guardrails and coherence mechanisms to ensure reliable agent behaviorDesign prompt engineering pipelines optimized for multi-turn, complex task executionOrchestrate Complex WorkflowsBuild end-to-end pipelines for multi-step task execution, tool integration, and iterative refinementDevelop coordination mechanisms for multi-agent collaboration and task delegationImplement feedback loops and self-improvement mechanismsDeploy Production-Ready SolutionsIntegrate agents with enterprise APIs, vector databases, and third-party systemsContainerize and deploy using Docker with CI/CD pipelinesEnsure secure, compliant, and fault-tolerant execution in production environmentsEnsure Performance & SafetyBuild comprehensive observability frameworks with tracing, logging, and performance monitoringImplement ethical AI safeguards including human-in-the-loop checkpoints and bias detectionOptimize for scalability, latency, and resource efficiency across distributed systemsRequired QualificationsTechnical ExpertiseStrong Python proficiency with production-level code qualityDeep experience with agentic AI frameworks: LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similarHands-on work with LLMs (GPT-4/5, Claude, Mistral, or Falcon) and fine-tuning techniquesProven ability to implement RAG systems, embedding models, and vector searchAI & ML FundamentalsSolid understanding of multi-agent orchestration patterns and coordination mechanismsExpertise in prompt engineering, context window management, and token optimizationKnowledge of memory systems (semantic, episodic, procedural) and state managementInfrastructure & DataExperience with vector databases (FAISS, Milvus, Pinecone, Weaviate)Familiarity with embedding models and semantic search pipelinesUnderstanding of observability tools and telemetry systemsAI Safety & EthicsAwareness of hallucination mitigation techniques and output validation strategiesKnowledge of compliance frameworks (GDPR, HIPAA, SOC 2) as they apply to AI systemsCommitment to responsible AI development practicesPreferred Qualifications5+ years of experience in AI/ML engineering roles2+ years specifically working with Agentic AI, autonomous systems, or multi-agent frameworksProduction deployment experience in cloud environments (Azure, AWS, GCP)Python expertise is requiredRUST experience is a plusContributions to open-source AI projects is a plusExperience with ML-Ops practices, model monitoring is a plusBackground in reinforcement learning is a plusHands on experience with Claude.AI LLM models is a plus