Senior AI Developer

Intetics — Slovenia · Posted ~4 hours ago

Senior Full-time Visa History ✓

Skills

LLM RAG Agentic AI AI Agents MCP Servers Python AI Architecture MCP Amazon Bedrock

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

A technology organization is seeking a senior AI developer to design and deploy production AI agents and intelligent systems. The role involves LLM applications, retrieval architectures, evaluation frameworks, integrations, and continuous improvement of AI solutions.

Highlights

Work on production-grade AI systems involving large language models, intelligent agents, retrieval architectures, and modern AI platforms.

Description

Intetics Inc., a leading American technology company specializing in custom software application development, distributed professional teams creation, software product quality assessment, and "all-things-digital" solutions, is looking for an AI Developer (LLM / RAG / Agentic AI) to join its innovative team. Project Responsibilities Design, build, and maintain LLM-based agents in production environments, both customer-facing and internalBuild MCP servers on top of existing databases and production systems, and orchestrate multiple internal and external MCP servers under a unified agent frameworkDesign and implement memory, context management, and RAG architectures for production useEstablish evaluation frameworks, handle edge cases, and continuously improve agent performance after releaseWork within architectures that combine databases, APIs, interfaces, agents, and orchestration applicationsDevelop AI solutions using Amazon Bedrock and/or Microsoft FoundryCollaborate with cross-functional teams to deliver scalable and reliable AI-powered products Candidate's Portrait We are looking for a hands-on AI Engineer (Middle+ to Senior level) who has successfully delivered AI agents into production and can clearly explain implementation challenges, failure cases, and optimization approaches. The ideal candidate is passionate about AI, actively explores new tools and models, and has a proven track record building intelligent systems beyond experimentation. 1.5-2+ years of hands-on experience with LLMs and AI agents in production environmentsStrong background in Machine Learning, Python development, or Data ScienceSelf-driven, innovative, and continuously learning emerging AI technologies Must-Haves 6+ years of overall experience in IT as a Software Engineer, ML Engineer, or AI EngineerHands-on production experience with Amazon Bedrock and/or Microsoft Foundry (Azure AI Foundry, Azure OpenAI)Proven experience building and deploying LLM-based agents to production, including customer-facing conversational AI and internal workflow automation agentsStrong experience with at least one agent framework: LangGraph, LangChain, LlamaIndex, Semantic Kernel, AutoGen, Strands Agents, or OpenAI Agents SDKDeep MCP expertise, including building MCP servers on top of existing databases and systems, integrating external MCP servers, and orchestrating multiple MCP services under a single agentStrong experience with production-grade RAG, memory, and context engineering, including: EmbeddingsChunking strategiesHybrid searchRerankingVector databasesShort-term and long-term agent memoryPractical experience implementing agentic patterns such as: ReActPlanner-ExecutorReflectionRouterSupervisorMulti-Agent SystemsHuman-in-the-LoopExperience with LLM evaluation, guardrails, monitoring, and iterative optimization based on production usage and failure analysisStrong understanding of system architecture involving databases, APIs, agents, and orchestration applicationsHands-on experience with Docker and CI/CD pipelines Nice-to-Have Experience in fintech, trading, investing, brokerage, or cryptocurrency-related productsBackground in regulated industries with strong requirements around compliance, data protection, and AI output auditabilityBroader AWS or Azure cloud expertise beyond AI servicesExperience with LLM evaluation and observability platforms such as LangSmith, Langfuse, Ragas, or custom evaluation pipelinesAdvanced practical expertise with modern agentic AI development tools and rapid prototyping approaches