Senior/Staff Software Engineer, Search & Retrieval Infrastructure

Pinecone is the leading AI knowledge platform trusted by over 10,000 customers and a million developers worldwide. The company provides a vector database and suite of tools that enable semantic search and hybrid retrieval for large language model applications. Pinecone's mission centers on making artificial intelligence truly knowledgeable by helping organizations connect their data to modern AI systems.

The Search & Retrieval Infrastructure team at Pinecone is growing to meet demand from enterprises building agent-based AI systems. As the market for AI infrastructure expands—with AI and ML engineering roles posting at 94.5% year-over-year growth in early 2026—companies like Pinecone need engineers who can architect systems that turn raw data into actionable knowledge for AI applications at scale.

You'll join the R&D team as a Senior or Staff Software Engineer, taking ownership of core platform components that power Pinecone's next-generation retrieval system. This role offers substantial architectural influence and the chance to shape how enterprises retrieve, process, and synthesize knowledge for agentic AI systems.

What you'll do

• Design and build scalable backend platform components that handle semantic search, hybrid retrieval, query planning, and metadata-aware filtering across structured and unstructured data
• Architect and optimize indexing pipelines that process diverse data formats at high throughput while maintaining data integrity and performance
• Develop backend services for knowledge graph construction, retrieval orchestration, and LLM integration patterns
• Create evaluation and observability frameworks that measure retrieval quality and system reliability in production
• Design APIs that serve both human developers and autonomous agents, prioritizing clarity and performance
• Optimize latency, throughput, and cost across large-scale inference and retrieval workloads
• Establish technical direction for system reliability and security across the platform

What you'll bring

• Six or more years of experience shipping production-grade backend systems at scale, with proven expertise in designing for high throughput, low latency, and maintainability
• Deep knowledge of modern retrieval technologies including vector databases, semantic search, hybrid retrieval strategies, and traditional search engines like Elasticsearch or OpenSearch
• Solid understanding of Retrieval-Augmented Generation patterns, embedding pipelines, and how query planning impacts LLM performance
• Expert proficiency in at least one major language such as Go, Rust, C++, Java, or Python
• Hands-on experience with cloud-native infrastructure, Kubernetes, observability systems, and infrastructure-as-code tools like Terraform or Pulumi
• Comfort designing high-throughput data pipelines that handle both structured schemas and messy unstructured data
• Strong product intuition and preference for owning problems end-to-end in fast-moving environments

Nice to have

• Experience building or scaling multi-tenant SaaS platforms
• Knowledge of retrieval evaluation frameworks and techniques for measuring search quality
• Background with query planning, agentic reasoning systems, or teaching AI systems to decompose complex problems

What they offer

• Comprehensive health coverage including medical, dental, vision, and mental health
• 401(k) plan with company contribution
• Equity awards
• Flexible time off policy
• Paid parental leave
• Annual company retreat
• Work-from-home equipment stipend