Senior Software Engineer, Search & Retrieval Infrastructure

Pinecone Systems Inc.

Job Overview

Location

US Remote

Job Type

Full-time

Full Job Description

📋 Description

• As a Senior Software Engineer on Pinecone’s Search & Retrieval Infrastructure team, you will play a pivotal role in shaping the core architecture of next-generation AI knowledge systems, enabling enterprises to build accurate, scalable, and secure agentic applications powered by vector search and retrieval-augmented generation (RAG). Your work will directly impact how organizations connect structured and unstructured data to large language models, driving innovation in AI-powered enterprise software.
• You will design and implement high-performance backend systems that power semantic and hybrid search, knowledge graph construction, and retrieval orchestration, ensuring low-latency, high-throughput operations at enterprise scale while maintaining rigorous standards for reliability, security, and observability.
• Pinecone is a market-leading vector database company trusted by over 9,000 customers across industries to accelerate AI application development. Backed by top-tier investors including Andreessen Horowitz and ICONIQ, we are building the foundational infrastructure for the AI era, and this role offers a unique opportunity to influence the technical direction of a high-growth, mission-driven organization.
• You will collaborate with a team of expert engineers focused on pushing the boundaries of retrieval systems, gaining deep expertise in applied AI infrastructure, distributed systems, and ML-powered search—skills that are increasingly critical as enterprises adopt generative AI at scale.
• Design and build scalable platform components leveraging advanced retrieval via query planning, semantic and hybrid search, metadata-aware search, and LLM generation, ensuring seamless integration between data sources and AI applications.
• Design and build optimized indexing pipelines for structured and unstructured data, handling diverse data formats and schemas while maintaining high throughput and fault tolerance in cloud-native environments.
• Build backend services for semantic and hybrid retrieval, knowledge graph construction, and retrieval orchestration, enabling sophisticated agentic workflows that break down complex queries into precise retrieval steps.
• Improve retrieval quality through evaluation and observability frameworks, implementing metrics-driven approaches to measure relevance, precision, and recall in hybrid search systems.
• Design APIs for internal and external user and agentic consumers, creating intuitive, well-documented interfaces that support both human developers and autonomous AI agents in retrieving knowledge efficiently.
• Optimize latency, throughput and cost across large-scale inference and retrieval workloads, using profiling, benchmarking, and infrastructure tuning to deliver cost-effective performance under variable loads.
• Drive technical direction for reliability and security, establishing best practices for fault tolerance, data protection, and system resilience in multi-tenant SaaS environments.

🎯 Requirements

• 6+ years of experience shipping production-grade backend systems for large-scale, distributed applications with a focus on high throughput, low latency, and long-term maintainability.
• Expertise in at least one major systems programming language such as Go, Rust, C++, Java, or Python, with demonstrated ability to write clean, efficient, and maintainable code.
• Hands-on experience with semantic search, vector databases, hybrid retrieval strategies, or traditional search engines like Elasticsearch or OpenSearch, including understanding of embedding pipelines and query planning.
• Familiarity with modern infrastructure tools including Kubernetes, cloud-native architectures, observability frameworks (e.g., Prometheus, Grafana), and infrastructure-as-code (Terraform, Pulumi).
• Proven ability to design and implement high-throughput indexing pipelines for both structured and unstructured data sources.
• Strong product thinking: ability to design clean, intuitive APIs for human and agentic users, balancing technical depth with usability.

🏖️ Benefits

• Comprehensive health coverage including medical, dental, vision, and mental health resources to support holistic well-being.
• 401(k) plan with company matching to help build long-term financial security.
• Equity award, offering direct ownership in Pinecone’s growth and success as a leader in AI infrastructure.
• Flexible time off policy enabling work-life balance and autonomy over scheduling.
• Paid parental leave to support employees during significant life events.
• Annual company retreat fostering team connection, collaboration, and culture in an in-person setting.
• WFH equipment stipend to ensure a productive and comfortable remote work environment.

Skills & Technologies

Python

Java

Rust

Kubernetes

Terraform

DevOps

Senior

Remote

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

Pinecone Systems Inc.

Visit Website

About Pinecone Systems Inc.

Pinecone provides a managed, cloud-native vector database that lets engineers build and scale machine-learning applications such as semantic search, recommendation systems, and retrieval-augmented generation. The platform automates indexing, sharding, and updates while offering low-latency approximate-nearest-neighbor queries at billions of vectors. It supports hybrid dense-sparse retrieval, metadata filtering, and real-time inserts and deletes. Available on AWS, GCP, and Azure, Pinecone handles infrastructure, security, and scaling so teams can focus on model development rather than operations.

View Company Profile

Get more remote jobs like this

Subscribe to the weekly newsletter for similar remote roles and curated hiring updates.

Weekly remote jobs and featured talent.

No spam. Only curated remote roles and product updates. You can unsubscribe anytime.