Job Description
This job was selected by the SpringCube team to help AI, Data and Cloud Engineers discover relevant San Francisco Bay Area employers. Sign up to view the full employer details and apply directly with the hiring company.
Company Overview
A technology company is developing AI agents designed to coordinate and optimize global supply chains. Its platform addresses significant inefficiencies across retail supply chains, including overproduction, lost revenue, and unnecessary emissions.
Key Responsibilities
- Build and maintain core data pipelines that transform unstructured and diverse inputs into clean, structured, and reliable datasets.
- Own end-to-end data ingestion, extraction, transformation, validation, and indexing workflows.
- Develop systems that interpret and map complex information into structured schemas.
- Reconcile inconsistencies across multiple data sources and establish reliable data validation processes.
- Design LLM-driven reasoning workflows for data extraction, interpretation, and decision support.
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines for retrieval and grounding.
- Architect and maintain a trusted, high-quality data store that serves as the foundation for downstream product systems.
- Develop APIs and data services that enable product and application teams to reliably consume structured data.
- Define and maintain data contracts in collaboration with product and application engineers.
- Ensure simulation systems and customer-facing features are powered by accurate, consistent, explainable, and production-ready data.
- Prototype rapidly using real customer inputs and iterate based on observed system performance.
- Debug ambiguous data and reasoning failures and develop solutions to improve system reliability.
- Harden data systems to scale with increasing product complexity and customer requirements.
- Apply strong data modeling and systems design principles across LLM, retrieval, and data engineering workflows.
- Establish data infrastructure that expands the product’s ability to understand, simulate, and deliver value to customers.
Required Qualifications
- Strong experience in data engineering, AI engineering, machine learning, or a closely related technical field.
- Experience building data pipelines and systems that process unstructured and structured data.
- Strong understanding of data modeling, data ingestion, transformation, validation, and indexing.
- Experience working with Large Language Models (LLMs) and AI-driven workflows.
- Hands-on experience developing RAG pipelines and retrieval systems.
- Understanding of data quality, schema design, data reconciliation, and validation techniques.
- Experience designing APIs and data services for production applications.
- Strong systems design and software engineering skills.
- Ability to work effectively with product and application engineering teams.
- Strong problem-solving skills and the ability to investigate ambiguous technical failures.
- Ability to prototype quickly, work with real-world customer data, and transition experimental systems into reliable production infrastructure.
- Strong interest in the intersection of LLMs, retrieval, data modeling, and systems engineering.
Preferred Qualifications
- Experience building AI-powered data platforms or intelligent data pipelines.
- Experience with vector databases, embedding systems, and retrieval infrastructure.
- Experience designing production-grade LLM applications.
- Experience working with complex, messy, or unstructured enterprise datasets.
- Experience in supply chain, retail, logistics, simulation, or optimization systems.
- Experience working in early-stage or high-growth technology environments.
- Ability to operate independently while collaborating closely with a small, highly technical engineering team.
Disclaimer
SpringCube curates tech job listings from various company websites to support tech professionals globally.
1.No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.
2.No Client Relationship: This company is not a client of SpringCube unless stated.
3.To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.
4.No Liability: SpringCube is not liable for inaccuracies.**
