The Software Engineering PMTS - Data Platform joins the AgentExchange Data Services team to own the data and intelligence architecture for the Agentforce marketplace. This role involves consolidating fragmented telemetry pipelines and ML signals into a unified, trusted data platform. You will build end-to-end data architecture, including canonical data models, streaming and batch ingestion, and schema governance. Key responsibilities include developing self-service analytics using Data 360 and Tableau Next, managing ML feature stores, and architecting an LLM-native data layer featuring RAG, embeddings, and vector stores. You will ensure data security through PII classification and multi-tenant isolation while providing technical leadership in cross-org architecture reviews. Required expertise includes Snowflake, BigQuery, Redshift, or Databricks, AWS-based platforms, and production LLM systems experience.
Own the end-to-end data architecture, canonical data models, and 18-month roadmap for the AgentExchange platform.
Design and enforce data contracts, streaming and batch ingestion pipelines, and schema governance across engineering teams.
Architect the LLM and agent-native data layer, including RAG strategies, vector stores, and MCP servers.
Build and maintain the ML platform for feature stores, training infrastructure, and predictive models like Lead Scoring.
Develop self-service analytics dashboards for GMV, attrition, and partner effort scores using Data 360 and Tableau.
Establish data security standards for PII handling, multi-tenant isolation, and GDPR/CCPA compliance across all AI surfaces.
Lead cross-org architecture reviews to align platform services and shared technical standards across the organization.
Mentor data engineers and analytics practitioners to improve technical craft and grow the next generation of senior talent.
What we're looking for
10+ years in software or data engineering, including multi-year ownership of an enterprise-scale data or ML platform.
Deep architecture experience in at least three of: lakehouse/warehouse design, streaming and batch pipelines, dimensional and event modeling, feature stores, or model serving.
Proficiency with cloud-native data infrastructure including Snowflake, BigQuery, Redshift, Databricks, and AWS-based platforms.
Production experience with LLM systems, including RAG, embeddings, vector stores, prompt engineering, and hallucination/safety controls.
Working knowledge of MCP or equivalent tool/agent protocols and experience with data security, governance, and PII classification.
Proven track record of technical leadership in cross-org architecture forums and influencing teams outside of your direct management.
Ability to communicate complex technical architectures and trade-offs to both executive and product management stakeholders.
Java
SQL
PL-SQL
Node.js
Express
Hapi
RDBMS
NoSQL
GenAI
LLM
RAG
Vector Search
Data Pipelines
Distributed Data Processing
Data Lake
Lakehouse
API Development
CI/CD
Agile
Streaming
Event-driven Architecture
Data Governance
Metadata Management