Key skills
PythonSQLAIMLLLMOpenAIAnthropicGeminiRAGLangChainAgenticAutoGenLangGraphChromaPineconeMilvusETLData EngineeringData WarehousingAnalyticsSnowflakeAirflowdbtAWSGCPSalesforceCRM
About this role
ITMC Systems, Inc is focused on building a new team within their Data Strategy & Operations function to transform data into actionable insights through agent-driven enrichment. The Senior Data Engineer will design and build intelligent data systems that automate data ingestion, validation, enrichment, and delivery to internal stakeholders and core Salesforce platforms.
Responsibilities:
- Build agentic capabilities to improve operational efficiency in third-party data ingestion and consumption
- Develop and manage data pipelines that ingest, enrich, and distribute data across systems
- Manage data egress from Data 360 to downstream platforms, including Salesforce CRM
- Reduce manual operational processes through automation and intelligent workflows
- Design and develop scalable ETL pipelines using Informatica, Python, and SQL
- Build and manage batch and real-time data pipelines across distributed systems
- Develop integrations using Airflow (orchestration) and MuleSoft (API/integration layer)
- Build and maintain data ingestion pipelines from third-party providers
- Own pipeline monitoring, troubleshooting, and optimization
- Implement data transformation and modeling using dbt
- Enable data egress patterns to deliver outputs to multiple downstream systems
- Track KPIs including data volume, pipeline performance, and ingestion success rates
- Collaborate with Product, Data Science, and Analytics teams for data consumption needs
- Build and onboard new data integrations into Data 360
- Develop agent-driven workflows to automate ingestion and enrichment processes
- Monitor pipeline performance and resolve production issues
- Drive data distribution to downstream platforms including Salesforce CRM
- Continuously optimize data workflows and reduce manual interventions
- Conduct deep discovery on a high-priority agentic use case and deliver an initial POC
- Begin productizing agent-driven workflows to improve operational efficiency
- Reduce manual validation and ingestion processes through automation
- Support integration and management of third-party data sources
Requirements:
- Strong experience in Data Engineering, ETL, and Data Architecture (Informatica preferred)
- Hands-on experience with Python, SQL, ETL frameworks, Airflow, Salesforce, and MuleSoft
- Strong experience with Snowflake or similar relational databases
- Experience building complex Python-based ETL modules and workflows
- Expertise in building batch and real-time data pipelines
- Experience with dbt for transformations and data modeling
- Familiarity with AWS and/or GCP environments
- Strong understanding of distributed systems and event-driven architectures
- Expertise in data modeling, data warehousing, and large-scale data processing
- Experience with data quality, monitoring, and orchestration frameworks
- Strong Python experience for AI/ML and application development
- Experience working with LLM APIs (OpenAI, Anthropic, Gemini) beyond basic use cases
- Hands-on experience with agentic frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or similar
- Experience building RAG pipelines and working with vector databases (Pinecone, Chroma, Milvus)
- Strong system design mindset — ability to decompose complex workflows into autonomous agent tasks
- Experience building multi-agent systems or multi-step autonomous workflows
- Exposure to Model Context Protocol (MCP) integrations
- Experience working with multi-modal agents (text, document, image processing)
- Experience with Salesforce Flows and Apex