We are looking for an AI Engineer (freelance) to join a project focused on building an AI-powered troubleshooting platform for large-scale IoT infrastructure. The platform leverages LLMs, retrieval systems, anomaly detection, and intelligent reasoning to help operators identify root causes of incidents and generate actionable recommendations. You will work on designing and improving the intelligence layer of the platform, contributing to cutting-edge AI solutions that solve real-world operational challenges. Responsibilities: • Design, develop, and improve AI-powered workflows for incident analysis and troubleshooting. • Build event classification, correlation, and reasoning pipelines. • Develop and optimize Retrieval-Augmented Generation (RAG) systems for technical documentation, troubleshooting guides, and historical incidents. • Create LLM-based root cause analysis and recommendation engines. • Design prompt engineering workflows, retrieval strategies, and reasoning pipelines. • Evaluate and improve the quality, accuracy, and reliability of AI-generated outputs. • Collaborate with Data Engineers on telemetry processing, feature generation, and data preparation. • Contribute to AI platform architecture, observability, and evaluation frameworks. • Analyze production incidents and continuously enhance AI troubleshooting capabilities. • Participate in testing, monitoring, and optimization of AI systems in production environments. Requirements: • Commercial experience building AI-powered products, intelligent automation systems, or AI applications. • Hands-on experience working with LLMs in production environments. • Experience building AI agents and agentic workflows. • Strong understanding of agent architectures, tool calling, context management, and custom tool integrations. • Experience with Model Context Protocol (MCP) or similar tool integration frameworks. • Strong understanding of Retrieval-Augmented Generation (RAG) architectures. • Experience with embeddings, vector search, and semantic retrieval. • Experience designing prompt workflows, structured outputs, and reasoning pipelines. • Understanding of AI evaluation methodologies and output quality measurement. • Understanding of anomaly detection, classification, and similarity search concepts. • Experience working with structured and semi-structured data. • Familiarity with telemetry data, event processing, or operational analytics. • Strong SQL skills and experience working with analytical datasets. • Strong Python development skills. • Experience building production-grade services and APIs. • Experience with asynchronous processing pipelines. • Experience working with PostgreSQL or similar relational databases. • Experience deploying AI applications in cloud environments. • Familiarity with AWS services and containerized deployments. • Understanding of monitoring, observability, and production support practices. • Experience with testing and CI/CD processes. • Upper-Intermediate English level or higher.
Nice to Have:
• Experience with AWS Bedrock. • Experience with LangGraph, LangChain, or similar orchestration frameworks. • Experience building multi-agent systems. • Experience with OpenSearch or vector databases. • Experience with LangSmith, LangFuse, or similar AI observability and evaluation platforms. • Experience working with IoT, telemetry, or operational infrastructure data.
Please note that feedback on the results of the CV review will be provided only in the event of a decision to consider your candidacy further. Otherwise, your data will be retained in the company’s CV database, and we will gladly contact you if a suitable vacancy becomes available. The consideration period is 7 working days.
Before sending us your CV, you may read our Privacy Notice.
