Senior/Staff Software Engineer, Search & Retrieval Infrastructure
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior/Staff Software Engineer, Search & Retrieval Infrastructure based in the United States.
This role sits at the core of next-generation AI knowledge systems, building the infrastructure that powers how modern applications retrieve, understand, and synthesize information at scale. You will design and develop high-performance backend systems that enable semantic search, hybrid retrieval, and LLM-augmented knowledge workflows across massive datasets. The work focuses on transforming both structured and unstructured data into reliable, queryable knowledge for AI-driven applications. You will own key architectural decisions spanning indexing pipelines, retrieval orchestration, and distributed backend services. The environment is deeply technical, fast-moving, and centered on large-scale AI infrastructure and system performance. Your contributions will directly impact the quality, speed, and reliability of retrieval systems used by thousands of developers and enterprises. This is a high-ownership role with significant influence on the future of AI-powered search.
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior/Staff Software Engineer, Search & Retrieval Infrastructure based in the United States.
This role sits at the core of next-generation AI knowledge systems, building the infrastructure that powers how modern applications retrieve, understand, and synthesize information at scale. You will design and develop high-performance backend systems that enable semantic search, hybrid retrieval, and LLM-augmented knowledge workflows across massive datasets. The work focuses on transforming both structured and unstructured data into reliable, queryable knowledge for AI-driven applications. You will own key architectural decisions spanning indexing pipelines, retrieval orchestration, and distributed backend services. The environment is deeply technical, fast-moving, and centered on large-scale AI infrastructure and system performance. Your contributions will directly impact the quality, speed, and reliability of retrieval systems used by thousands of developers and enterprises. This is a high-ownership role with significant influence on the future of AI-powered search.
Accountabilities:
- Design and build scalable search and retrieval infrastructure, including semantic search, hybrid retrieval, metadata-aware querying, and LLM-driven query planning systems.
- Develop high-throughput indexing pipelines for both structured and unstructured data, ensuring performance, reliability, and scalability.
- Build and maintain backend services that support retrieval orchestration, knowledge synthesis, and agentic AI workflows.
- Improve retrieval quality through robust evaluation frameworks, observability systems, and experimentation on ranking and relevance.
- Design clean, intuitive, and scalable APIs for both internal systems and external developer and agentic use cases.
- Optimize system performance across latency, throughput, and cost in large-scale distributed environments.
- Drive technical direction for reliability, security, and architectural evolution of core retrieval systems.
- Collaborate closely with cross-functional teams to align infrastructure capabilities with product and AI application needs.
- Contribute to system-level design decisions that shape long-term platform scalability and extensibility.
- 6+ years of experience building production-grade backend systems in large-scale distributed environments.
- Strong expertise in system architecture, with a focus on high throughput, low latency, and scalable design principles.
- Experience building or working with search systems, including semantic search, vector databases, hybrid retrieval, or platforms like Elastic or OpenSearch.
- Deep understanding of retrieval-augmented generation (RAG), embedding pipelines, and LLM-based orchestration patterns.
- Proficiency in at least one major programming language such as Go, Rust, C++, Java, or Python.
- Experience with data engineering and building large-scale indexing pipelines for diverse data types.
- Familiarity with modern infrastructure tools such as Kubernetes, cloud-native architectures, observability systems, and IaC tools like Terraform or Pulumi.
- Strong product mindset with the ability to design developer-friendly and agent-friendly APIs.
- Comfortable working in ambiguous, high-growth environments with significant ownership expectations.
- Strong problem-solving skills and a bias toward building robust, long-term systems rather than short-term fixes.
- Bonus: experience with multi-tenant SaaS systems, retrieval evaluation frameworks, or agentic query planning systems.
- Comprehensive medical, dental, vision, and mental health coverage
- 401(k) retirement plan
- Equity compensation package
- Flexible PTO policy
- Paid parental leave
- Annual company retreat and offsites
- Home office equipment stipend
- Inclusive and collaborative engineering culture focused on AI innovation
- Opportunity to work on cutting-edge AI search and retrieval infrastructure at scale.