Database Engineer - RAG Platform Developer

We're seeking a Database Engineer to architect and optimize our large-scale RAG

(Retrieval-Augmented Generation) platform that serves our users across all of

the Hardware Tech group. This role combines deep database expertise with modern

AI/ML infrastructure, enabling design teams to seamlessly onboard and query

enterprise-scale datasets. You'll be responsible for database architecture and

optimization while also contributing to full-stack GenAI application

development.

DESCRIPTION

As a Database Engineer on our team, you will architect and optimize our SQL and

vector database infrastructure supporting enterprise-scale design data. You'll

lead technical decisions on database architecture, scaling patterns, and

technology selection for our RAG platform while designing comprehensive

strategies to ensure optimal performance. Working closely with the development

team, you'll build and refine data ingestion pipelines that enable design teams

across all disciplines to seamlessly onboard their data. You'll collaborate with

DevOps/SRE teams to ensure quality of service, proper resource allocation, and

system scalability while improving RAG retrieval performance through hybrid

search strategies, index tuning, and embedding optimization. In addition to your

primary database focus, you'll contribute to full-stack development using Python

and JavaScript, monitor database health and performance metrics for our

multi-tenant system, and develop and maintain database operations procedures,

monitoring, and disaster recovery strategies while driving continuous

improvement of retrieval quality, search latency, and overall system

reliability. You'll also provide mentorship to other engineers on database best

practices and scalable design patterns.

MINIMUM QUALIFICATIONS

Proficiency in Python or Javascript. Production experience deploying and

managing vector databases (Milvus, Qdrant, or Weaviate) at scale Experience with

PostgreSQL or MySQL in production environments Understanding of RAG pipelines,

including embedding strategies, chunking, and retrieval optimization Minimum

requirement of BS + 10 years of relevant industry experience

PREFERRED QUALIFICATIONS

Understanding of Vector database indexing strategies and tradeoffs Strong SQL

proficiency with deep understanding of query planning, indexing strategies, and

optimization techniques Postgres advanced features (extensions, replication,

sharding) Experience managing large-scale databases serving high-concurrency

workloads Experience with embedding models and LLM integration patterns

Demonstrated experience building or optimizing RAG systems in production

environments Collaborative mindset with ability to mentor engineers and work

closely with DevOps/SRE teams Monitoring and observability tools (Prometheus,

Grafana) Kubernetes experience, particularly with stateful applications and

database deployments Proven ability to make architectural decisions for scalable

database systems