Staff Software Engineer I (Open)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Location: Hybrid; United States of America, Eagan, Minnesota. Other locations: United States of America, Frisco, Texas; Canada, Toronto, Ontario. Work from anywhere is available for up to 8 weeks per year.
Base compensation: $118,400–$219,800 USD for eligible US locations; $140,600–$190,600 CAD for Ontario, Canada. The role may also be eligible for an annual bonus.
Company
provides trusted content, software, and insights for legal, tax, accounting, compliance, government, and media professionals.
What you will do
- Set the architecture, design patterns, schemas, contribution standards, and API contracts for the Content Tools catalog.
- Architect retrieval and search on the Vespa-based platform, balancing structured and semantic retrieval, ranking quality, relevance, and latency.
- Define MCP-based agent invocation patterns and build shared Python, FastAPI, Claude Agent SDK, testing, scaffolding, mock-service, and local-development infrastructure.
- Establish verified spec-driven development, evaluation datasets, IR metrics, offline and online grading, and CI gates for tool quality.
- Own reliability, SLOs, on-call operations, incident response, observability, capacity planning, caching, rate limiting, and cost management.
- Provide cross-team technical leadership, mentor Senior engineers, document architecture decisions, and promote secure, ethical AI-assisted development.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
- 8+ years of software engineering experience with progression to staff-level or equivalent technical leadership, including functional-area ownership and significant cross-team initiatives.
- Mastery of Python and strong fundamentals in API design, unit, integration, load and evaluation testing, system design, and security architecture.
- Experience designing and operating API-first systems used by multiple teams, including versioning, backward compatibility, clear contracts, and developer-experience ownership.
- Working fluency with information retrieval, including precision/recall trade-offs, hybrid search, ranking, and citation networks.
- Experience designing or owning evaluation frameworks for retrieval or LLM systems, including dataset design, IR metrics, CI-gated evaluation suites, tracing, and observability for non-deterministic workflows.
- System-level reliability ownership, including on-call models, SLOs, incident response, and frequent reliable delivery.
- Demonstrated security and access-control practice; strong communication across engineering, product, science, and non-technical audiences.
- Fluency with AI-assisted development tools and willingness to write the majority of code with AI assistance while establishing team-wide practices.
Nice to have
- Experience building tools or APIs for agentic AI systems, including MCP or similar protocols.
- Legal technology, knowledge management, or other high-stakes information-domain experience involving attribution, accuracy, and entitlement enforcement.
- Experience operating OpenSearch, Vespa, or Elasticsearch, including cluster sizing, index lifecycle, and semantic versus structured search trade-offs.
- Experience with LLM workflow tooling, prompt engineering, agent invocation patterns, contribution governance, content licensing, and multi-tenant entitlements.
- Working knowledge of Terraform and API gateways such as Apigee.
Culture & Benefits
- Flexible hybrid work environment with digitally and physically connected collaboration.
- Work-life-balance policies, flexible vacation, two company-wide Mental Health Days, paid holidays, parental leave, and sabbatical leave.
- Health, dental, vision, disability, life insurance, retirement savings, 401k matching in the US, FSA/HSA, fitness reimbursement, and employee assistance programs.
- Tuition reimbursement, learning and development programs, employee incentive and stock purchase plans, and two paid volunteer days annually.
- AI is used in recruitment unless the candidate opts out; final consideration includes human review.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →