AI Engineer
Ncs · Singapore
Role SummaryYou are an autonomous AI Engineer, responsible for creating the harness for designing and building the AI harness, agent framework, and reusable engineering components required to operate a modern data platform based on Apache Iceberg, Trino, and Parquet.Your primary responsibility is not only to build data pipelines, but also to establish the agentic execution framework (AIHarness) that enables multiple specialized agents to collaborate, execute tasks, maintain state, orchestrate workflows, and deliver end-to-end data engineering capabilities.Key ResponsibilitiesAI Harness DevelopmentDesign and implement the foundational agent framework that provides:Agent orchestration and coordinationWorkflow execution and state managementMemory and context handlingTool and function callingAgent-to-agent communicationHuman approval workflowsLogging and audit trailsError handling and recoverySecurity and access controlsObservability and monitoringThe harness must support autonomous and multi-agent execution patterns.Specialized Agents CreationThe agents will need to perform the following:Discover Iceberg catalogs and schemasProfile datasetsGenerate metadata and lineageIngest data from databases, APIs, files, and streamsCreate Parquet datasetsRegister and maintain Iceberg tablesGenerate Trino SQLBuild transformation workflowsCreate curated and business-ready datasetsValidate schemas and data integrityDetect anomaliesGenerate reconciliation reportsAnalyze Trino workloadsRecommend partitioning strategiesOptimize Iceberg tables and Parquet filesClassify sensitive informationManage metadata and lineageApply retention and compliance policiesMonitor pipelines and agent activitiesDetect failures and bottlenecksGenerate alerts and operational insight Expected DeliverablesIceberg table definitions and schemasTrino SQL scripts and viewsPython data pipeline codeData quality validation suitesMetadata and lineage documentationCI/CD deployment artifactsMonitoring and observability configurationsTechnical documentation and runbookSkills and ExperienceThe candidate should demonstrate expertise in:Experience with Generative AI, Agentic AI, or LLM-based solutions. Proficiency in Python, including FastAPI, Pydantic and Pandas. Experience designing and implementing AI Harness or multi-agent frameworks. Hands-on experience with LangChain & LangGraph. Experience with Apache Iceberg, Trino, and Parquet-based lakehouse architectures. Experience building data ingestion, transformation, and orchestration pipelines. Strong knowledge of meta data management, data lineage, and data governance practices. Experience developing REST APIs,SDKs, and reusable engineering frameworks. Experience with observability, monitoring, tracing, and operational support practices. Strong understanding of distributed systems, event-driven architectures, and microservices patterns. Proven ability to design, develop, and operationalize enterprise-grade AI agents for data discovery, ingestion, transformation, optimization, governance, and observability.Familiar with modern data engineering technologies, including DuckDB, dbt, and related engineering tools for data transformation, modelling, and pipeline development.