Senior/Staff Software Engineer, Search & Retrieval Infrastructure
$190k - $270k • Remote • US Remote • FullTime
Posted 2mo ago
Job Location
US Remote
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
RAG Engineer
About the job
Pinecone is seeking a Senior/Staff Software Engineer to join their team and contribute to the design and development of their next-generation knowledge retrieval system. This role focuses on building core components for search and retrieval infrastructure that powers scalable, enterprise-grade agentic systems. You will be instrumental in creating the framework that connects synthesized knowledge from various data sources to modern LLM-powered applications, utilizing Pinecone's vector database for semantic and hybrid search. This is a high-impact position offering significant ownership over architecture, performance, and system reliability, ideal for individuals passionate about backend systems, distributed systems, and applied AI infrastructure.
Responsibilities
- Design and build scalable platform components for advanced retrieval, including query planning, semantic and hybrid search, metadata-aware search, and LLM generation.
- Develop optimized indexing pipelines for both structured and unstructured data.
- Construct backend services for semantic and hybrid retrieval, knowledge graph construction, and retrieval orchestration.
- Enhance retrieval quality through the implementation of evaluation and observability frameworks.
- Create APIs for internal and external users, as well as agentic consumers.
- Optimize latency, throughput, and cost for large-scale inference and retrieval workloads.
- Lead technical direction for reliability and security initiatives.
Requirements
- Typically 6+ years of experience shipping production-grade backends for large-scale systems, with a focus on high throughput, low latency, and maintainability.
- Experience building high-throughput indexing pipelines for both unstructured and structured data.
- Direct experience or deep theoretical knowledge in semantic search, vector databases, hybrid retrieval strategies, or traditional search engines (e.g., Elastic, OpenSearch).
- Understanding of Retrieval-Augmented Generation (RAG) patterns, including embedding pipelines, hybrid search, query planning, and metadata filtering.
- Expertise in at least one major programming language such as Go, Rust, C++, Java, or Python.
- Familiarity and experience with modern infrastructure tools like Kubernetes, cloud-native architectures, observability frameworks, and infrastructure-as-code tools (e.g., Terraform, Pulumi).
- Product thinking skills to design clean, intuitive APIs for human developers and autonomous agents.
- Comfort navigating ambiguity in a high-growth environment and taking ownership of problems.
Benefits
- Comprehensive health coverage (medical, dental, vision, mental health)
- 401(k) Plan
- Equity award
- Flexible time off
- Paid parental leave
- Annual Company Retreat
- WFH Equipment Stipend