Senior/Staff Software Engineer, Search & Retrieval Infrastructure

Jobgether·Lever
United StatesFull-timePosted Jul 2, 2026
Open original posting

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.
    • Requirements

      • 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.
      • Benefits

        • 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.
How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best!  Why Apply Through Jobgether?    Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.     #LI-CL1

Want jobs like this matched to you?

Swoopd scores fresh postings against your résumé so you only see the matches that matter.

Get started free