Staff Software Engineer, Search Retrieval Platform
About The Position
Advanced Content Engineering (ACE) is seeking a Staff Software Engineer to build platform capabilities that let product teams, research teams, and AI agents access high-quality, customizable search without building it from scratch. The role focuses on making retrieval a fully customizable, plug-and-play service by understanding customer needs and translating them into reusable platform capabilities. The engineer will work closely with product, research engineering, and applied science partners across APIs, search services, agents, evaluation and grading, authentication, and security. The platform serves end customers, AI agents, and internal systems at enterprise scale. Staff Engineers define, build, deploy, and operate what they ship; the team ships to production constantly and uses AI-assisted development as the norm. The role includes setting architectural direction for retrieval, search services, and APIs; leading cross-team initiatives; mentoring engineers; and balancing near-term product needs with long-term platform goals. Success includes learning the platform architecture and gaps, building relationships across teams, taking on-call ownership, delivering improvements to retrieval, and enabling client teams to configure retrieval capabilities independently.
Requirements
- At least 8 years of software engineering experience with progression to staff-level scope, including functional-area ownership and cross-functional leadership.
- A degree in Computer Science, Engineering, or a related field, or equivalent experience.
- Experience building search, retrieval, or data-intensive platforms at scale, with strong distributed systems fundamentals and a language such as Python, Java, or Go.
- Track record of translating customer needs into platform capabilities and working across product, engineering, and science.
- Experience designing APIs and services consumed by multiple teams, with attention to contracts, versioning, and developer experience.
- Operational rigor, including SLOs, observability, on-call ownership, and learning from incidents.
- Fluency with AI-assisted development tools.
Nice To Haves
- Production experience with search engines such as Vespa, OpenSearch, or Elasticsearch.
- Experience with hybrid dense and sparse retrieval, ranking, and embedding pipelines.
- Experience building tools or APIs for AI agents, including agentic retrieval patterns and protocols such as MCP.
- Search evaluation experience, including relevance metrics, LLM-as-judge, and online experimentation.
- Experience with multi-tenant authentication, authorization, and entitlements.
- Experience operationalizing ML models in production, including serving, promotion, and monitoring.
Responsibilities
- Translate customer and product needs into reusable platform capabilities by working directly with product teams, client teams, and agent builders.
- Design retrieval APIs and search services for end users, AI agents, and internal systems, including consistent contracts, tunable filtering and ranking, predictable latency, and payloads suited to agent context windows.
- Make retrieval customizable through pluggable components for chunking, enrichment, embedding, ranking, and custom models, configurable through self-service APIs.
- Own content ingestion and indexing, including streaming pipelines, search engine configuration, and zero-downtime index changes.
- Partner with Research Engineering and Applied Science to move retrieval techniques from experiments to supported platform capabilities with a path to production.
- Work with product and client teams to prioritize the roadmap, incorporate adoption feedback, and reduce time-to-value for new adopters.
- Build evaluation into the platform, including offline evaluation, search grading, LLM-as-judge scoring, and online experiments.
- Own retrieval security, including multi-tenant data isolation, query-time entitlements, and telemetry that protects user content.
- Own SLOs, observability, and on-call for delivered systems; include tracing for agentic retrieval paths and drive improvements from incident reviews.
- Set architectural direction and design patterns across retrieval, search services, and APIs, acting as a technical authority.
- Lead cross-team initiatives, set priorities, and make trade-offs between near-term product needs and long-term platform goals.
- Mentor Senior and mid-level engineers and help the team use AI-assisted development effectively.
Benefits
- Comprehensive health, dental, vision, disability, and life insurance programs.
- Competitive 401(k) plan with company match.
- Flexible vacation, sick and safe paid time off, and paid holidays, including two company-wide mental health days.
- Parental leave and sabbatical leave.
- Access to the Headspace app and Employee Assistance Program.
- Tuition reimbursement.
- Employee incentive programs and an employee stock purchase plan.
- Fitness reimbursement.
- Flexible Spending and Health Savings Accounts.
- Commuter benefits.
- Adoption and surrogacy assistance.
- Optional hospital, accident and sickness insurance, optional life and AD&D insurance, and group legal identity theft protection, paid 100% by the employee.
- Access to a 529 Plan.
- Two paid volunteer days annually and opportunities for pro-bono consulting and ESG initiatives.
- Flexible hybrid work arrangements, including work from anywhere for up to 8 weeks per year.
- Career development and continuous learning programs.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
