[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"seo-content-skill-pyspark-sg":3,"job-search-\u002Fen-sg\u002Fjobs-by-skill\u002Fpyspark":8,"skill-page-filters-\u002Fen-sg\u002Fjobs-by-skill\u002Fpyspark":136,"featured-jobs-\u002Fen-sg\u002Fjobs-by-skill\u002Fpyspark":259},{"image_path":4,"content_de":5,"content_en":5,"composite_key":6,"last_updated":7},"\u002Fimages\u002Fskill\u002Fpyspark.webp",null,"skill:pyspark:sg","2026-08-17T09:02:50.200472+02:00",{"total":9,"jobs":10},3,[11,61,79],{"id":12,"slug":13,"title":14,"raw_title":5,"is_featured":15,"company":16,"raw_hiringOrganization_logo_url":5,"processed_city_gmaps":19,"processed_country_iso_code_gmaps":20,"processed_home_office":22,"processed_salary_min":23,"processed_salary_max":24,"processed_salary_currency":25,"processed_salary_source":26,"processed_working_hours":27,"processed_employment_types":29,"processed_it_skills":30,"processed_it_skills_labels":32,"processed_job_expertise_skills":48,"processed_job_expertise_skills_labels":49,"max_cpc":60,"actual_cpc":60},76532,"senior-data-engineer-ocbc-bank","Senior Data Engineer",false,{"name":17,"slug":18,"logo_url":5},"OCBC Bank","ocbc-bank",[],[21],"SG","onsite",90000,150000,"SGD","estimated",[28],"FULL_TIME","permanent",{"c++":9,"git":9,"sql":31,"java":9,"spark":31,"python":31,"datahub":9,"etl\u002Felt":31,"pyspark":31,"openmetadata":9,"apache iceberg":31,"cloud platforms":31,"streaming systems":31,"open data catalogue":9,"unix\u002Flinux shell scripting":9},4,[33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"Spark","PySpark","Apache Iceberg","Streaming Systems","Open Data Catalogue","OpenMetadata","DataHub","Python","Unix\u002FLinux Shell Scripting","SQL","ETL\u002FELT","Cloud Platforms","Java","C++","Git",{"data migration":31,"data governance":9,"agile methodologies":9,"data quality checks":9,"metadata management":9,"data pipeline design":31,"software development":9,"cloud-native data engineering":31,"data lakehouse implementation":31,"real-time streaming pipelines":31},[50,51,52,53,54,55,56,57,58,59],"Cloud-Native Data Engineering","Data Pipeline Design","Data Lakehouse Implementation","Real-Time Streaming Pipelines","Data Migration","Data Governance","Metadata Management","Data Quality Checks","Agile Methodologies","Software Development",1,{"id":62,"slug":63,"title":14,"raw_title":5,"is_featured":15,"company":64,"raw_hiringOrganization_logo_url":5,"processed_city_gmaps":65,"processed_country_iso_code_gmaps":66,"processed_home_office":22,"processed_salary_min":23,"processed_salary_max":24,"processed_salary_currency":25,"processed_salary_source":26,"processed_working_hours":67,"processed_employment_types":29,"processed_it_skills":68,"processed_it_skills_labels":69,"processed_job_expertise_skills":71,"processed_job_expertise_skills_labels":72,"max_cpc":60,"actual_cpc":60},76533,"senior-data-engineer-ocbc-bank-2",{"name":17,"slug":18,"logo_url":5},[],[21],[28],{"c++":9,"git":9,"sql":31,"java":9,"python":31,"datahub":9,"etl\u002Felt":31,"pyspark":31,"apache spark":31,"openmetadata":9,"apache iceberg":31,"cloud platforms":31,"streaming systems":31,"agile methodologies":9,"open data catalogue":9,"unix\u002Flinux shell scripting":9},[40,42,70,34,35,36,44,43,41,37,38,39,45,46,47,58],"Apache Spark",{"data quality":9,"data lakehouse":31,"data migration":31,"data pipelines":31,"data governance":9,"data engineering":31,"real-time processing":31,"software development":9,"cloud-native architecture":31},[73,74,75,76,77,54,55,78,59],"Data Engineering","Cloud-Native Architecture","Data Pipelines","Data Lakehouse","Real-Time Processing","Data Quality",{"id":80,"slug":81,"title":82,"raw_title":5,"is_featured":15,"company":83,"raw_hiringOrganization_logo_url":5,"processed_city_gmaps":84,"processed_country_iso_code_gmaps":85,"processed_home_office":22,"processed_salary_min":86,"processed_salary_max":87,"processed_salary_currency":25,"processed_salary_source":26,"processed_working_hours":88,"processed_employment_types":29,"processed_it_skills":89,"processed_it_skills_labels":91,"processed_job_expertise_skills":114,"processed_job_expertise_skills_labels":115,"max_cpc":60,"actual_cpc":60},62344,"data-engineer-vp-ocbc-bank","Data Engineer (VP)",{"name":17,"slug":18,"logo_url":5},[],[21],120000,180000,[28],{"aws":31,"dbt":9,"git":9,"sql":31,"ci\u002Fcd":9,"kafka":9,"docker":9,"hadoop":9,"python":31,"airflow":9,"dagster":9,"kinesis":9,"pyspark":31,"pinecone":90,"power bi":9,"weaviate":90,"langchain":90,"sagemaker":90,"terraform":90,"databricks":9,"kubernetes":9,"opensearch":90,"apache spark":31,"amazon bedrock":90,"apache iceberg":31,"cloudformation":90,"data virtualization":9,"unix\u002Flinux shell scripting":9},2,[42,70,34,40,35,92,93,94,47,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"dbt","Airflow","Dagster","CI\u002FCD","Unix\u002FLinux shell scripting","AWS","Kafka","Kinesis","Hadoop","Data Virtualization","Power BI","Docker","Kubernetes","Amazon Bedrock","SageMaker","Databricks","OpenSearch","LangChain","Pinecone","Weaviate","Terraform","CloudFormation",{"mlops":9,"banking":9,"dataops":31,"data mesh":90,"data lineage":31,"ai governance":90,"data products":90,"generative ai":9,"vector search":9,"responsible ai":90,"data governance":31,"data engineering":31,"machine learning":9,"data observability":31,"financial services":9,"distributed systems":9,"feature engineering":9,"metadata management":31,"lakehouse architecture":31,"cloud-native architecture":31,"data platform architecture":31,"large language models (llms)":90,"retrieval-augmented generation (rag)":9},[73,116,117,118,55,119,56,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135],"Data Platform Architecture","Cloud-native Architecture","Lakehouse Architecture","Data Lineage","Data Observability","DataOps","MLOps","Machine Learning","Generative AI","Retrieval-Augmented Generation (RAG)","Feature Engineering","Vector Search","Data Mesh","Data Products","Distributed Systems","Large Language Models (LLMs)","Responsible AI","AI Governance","Financial Services","Banking",{"industry":137,"employment_type":142,"expertise_skills":145,"it_skills":198,"salary_currency":255,"processed_working_hours":257},[138,140],{"key":139,"label":134,"count":9},"financial services",{"key":141,"label":135,"count":90},"banking",[143],{"key":29,"label":144,"count":9},"PERMANENT",[146,148,150,152,154,156,158,160,162,164,166,168,170,172,174,176,179,181,183,185,188,190,193,195],{"key":147,"label":55,"slug":147,"count":9},"data-governance",{"key":149,"label":73,"slug":149,"count":90},"data-engineering",{"key":151,"label":74,"slug":151,"count":90},"cloud-native-architecture",{"key":153,"label":56,"slug":153,"count":90},"metadata-management",{"key":155,"label":59,"slug":155,"count":90},"software-development",{"key":157,"label":54,"slug":157,"count":90},"data-migration",{"key":159,"label":119,"slug":159,"count":60},"data-lineage",{"key":161,"label":128,"slug":161,"count":60},"data-mesh",{"key":163,"label":120,"slug":163,"count":60},"data-observability",{"key":165,"label":51,"slug":165,"count":60},"data-pipeline-design",{"key":167,"label":75,"slug":167,"count":60},"data-pipelines",{"key":169,"label":116,"slug":169,"count":60},"data-platform-architecture",{"key":171,"label":129,"slug":171,"count":60},"data-products",{"key":173,"label":78,"slug":173,"count":60},"data-quality",{"key":175,"label":57,"slug":175,"count":60},"data-quality-checks",{"key":177,"label":178,"slug":177,"count":60},"dataops","Dataops",{"key":180,"label":130,"slug":180,"count":60},"distributed-systems",{"key":182,"label":126,"slug":182,"count":60},"feature-engineering",{"key":184,"label":134,"slug":184,"count":60},"financial-services",{"key":186,"label":187,"slug":186,"count":60},"generative-ai","Generative Ai",{"key":189,"label":118,"slug":189,"count":60},"lakehouse-architecture",{"key":191,"label":192,"slug":191,"count":60},"large-language-models-llms","Large Language Models (Llms)",{"key":194,"label":123,"slug":194,"count":60},"machine-learning",{"key":196,"label":197,"slug":196,"count":60},"mlops","Mlops",[199,201,203,206,208,210,212,214,217,219,221,223,226,229,231,233,236,239,241,244,247,249,251,253],{"key":200,"label":35,"slug":200,"count":9},"apache-iceberg",{"key":202,"label":47,"slug":202,"count":9},"git",{"key":204,"label":205,"slug":204,"count":9},"pyspark","Pyspark",{"key":207,"label":40,"slug":207,"count":9},"python",{"key":209,"label":42,"slug":209,"count":9},"sql",{"key":211,"label":41,"slug":211,"count":9},"unixlinux-shell-scripting",{"key":213,"label":36,"slug":213,"count":90},"streaming-systems",{"key":215,"label":216,"slug":215,"count":90},"datahub","Datahub",{"key":218,"label":45,"slug":218,"count":90},"java",{"key":220,"label":44,"slug":220,"count":90},"cloud-platforms",{"key":222,"label":37,"slug":222,"count":90},"open-data-catalogue",{"key":224,"label":225,"slug":224,"count":90},"openmetadata","Openmetadata",{"key":227,"label":228,"slug":227,"count":90},"etlelt","Etl\u002FElt",{"key":230,"label":46,"slug":230,"count":90},"c",{"key":232,"label":70,"slug":232,"count":90},"apache-spark",{"key":234,"label":235,"slug":234,"count":60},"langchain","Langchain",{"key":237,"label":238,"slug":237,"count":60},"opensearch","Opensearch",{"key":240,"label":110,"slug":240,"count":60},"pinecone",{"key":242,"label":243,"slug":242,"count":60},"ms-powerbi","MS PowerBI",{"key":245,"label":246,"slug":245,"count":60},"sagemaker","Sagemaker",{"key":248,"label":33,"slug":248,"count":60},"spark",{"key":250,"label":112,"slug":250,"count":60},"terraform",{"key":252,"label":58,"slug":252,"count":60},"agile-methodologies",{"key":254,"label":111,"slug":254,"count":60},"weaviate",[256],{"key":25,"label":25,"count":9},[258],{"key":28,"label":28,"count":9},{"total":260,"jobs":261},0,[]]