3 months ago
Remote, United StatesSenior / Staff+
H1B sponsor
Base Salary
$190k - $270k/yr
Responsibilities
- Design and build scalable platform components for query planning, semantic search, hybrid search, metadata-aware search, and LLM generation.
- Build optimized indexing pipelines for structured and unstructured data.
- Develop backend services for semantic and hybrid retrieval, knowledge graph construction, and retrieval orchestration.
- Improve retrieval quality through evaluation and observability frameworks.
- Design APIs for internal and external users and agentic consumers.
- Optimize latency, throughput, and cost across large-scale inference and retrieval workloads.
- Drive technical direction for system reliability and security.
Requirements
- Typically 6+ years of experience shipping production-grade backends for large-scale systems.
- Demonstrated architectural depth designing high-throughput, low-latency, maintainable systems.
- Experience building high-throughput indexing pipelines for structured and unstructured data.
- Direct experience or deep theoretical knowledge of semantic search, vector databases, hybrid retrieval, Elastic, or OpenSearch.
- Understanding of Retrieval-Augmented Generation patterns, embedding pipelines, hybrid search, query planning, and metadata filtering.
- Expertise in at least one major language such as Go, Rust, C++, Java, or Python.
- Familiarity with Kubernetes, cloud-native architectures, observability frameworks, and infrastructure-as-code tools such as Terraform or Pulumi.
- Ability to design clean APIs for human developers and autonomous agents and take ownership of ambiguous, high-impact problems.
- Experience with multi-tenant SaaS platforms, retrieval evaluation frameworks, query planning, or agentic reasoning loops is a bonus.
Benefits
- Comprehensive medical, dental, vision, and mental health coverage.
- 401(k) plan.
- Equity award.
- Flexible time off.
- Paid parental leave.
- Annual company retreat.
- WFH equipment stipend.
Categories
About Pinecone
Pinecone builds a managed vector database and knowledge engine used by developers and ML teams to power search, retrieval, and other AI application features. It sells a cloud service with APIs and tooling for production-scale similarity search and retrieval-augmented generation. Founded in 2019 and headquartered in New York, the privately held company serves enterprises and startups building generative AI and search experiences.