Staff Backend Engineer - AI Retrieval & Vector DB

Pinecone; New York (NY); On-site; USD 180,000 - 250,000; Full time

Benefits offered by this job

Health coverage

401(k) Plan

Equity award

Flexible time off

Parental leave

Annual retreat

WFH stipend

Job summary

Pinecone is hiring a senior/staff software engineer to build core components of a next-generation knowledge retrieval system, supporting semantic search and hybrid retrieval for AI applications. You will own backend architecture, performance, and reliability across large-scale inference workloads.

The role emphasizes distributed systems, backend design, and ownership with strong emphasis on API quality and multi-tenant SaaS considerations. Based in New York area.

Qualifications

• 6+ years shipping production-grade backends for large-scale systems.
• Experience building high-throughput indexing pipelines for unstructured and structured data.
• Experience with semantic search, vector databases, or traditional search engines.
• Understanding of RAG patterns and embedding pipelines for LLMs.
• Expertise in Go, Rust, C++, Java, or Python.
• Experience with Kubernetes, cloud-native architectures and observability tools.
• Familiarity with Terraform or Pulumi and multi-tenant SaaS platforms.

Responsibilities

• Design and build scalable platform components for retrieval with semantic and hybrid search.
• Design and build optimized indexing pipelines for structured and unstructured data.
• Build backend services for knowledge graph construction and retrieval orchestration.
• Improve retrieval quality through evaluation and observability frameworks.
• Design APIs for internal and external user and agentic consumers.
• Optimize latency, throughput and cost across large-scale inference and retrieval workloads.
• Drive technical direction for reliability and security.

Skills

Architectural depth

Data engineering

Semantic search

RAG & orchestration

API design

Programming languages

Kubernetes

Cloud-native

Observability

Education

Bachelor's degree in CS or related

Tools

OpenSearch/Elastic

Terraform/Pulumi

Kubernetes

Vector databases

Job description

Pinecone is hiring a senior/staff software engineer to build core components of a next-generation knowledge retrieval system, supporting semantic search and hybrid retrieval for AI applications. You will own backend architecture, performance, and reliability across large-scale inference workloads.

The role emphasizes distributed systems, backend design, and ownership with strong emphasis on API quality and multi-tenant SaaS considerations. Based in New York area.