Staff Backend Engineer - Second Horizon
This Staff Backend Engineer will design and operate production backend services for an AI-native enterprise context system, including ingestion, indexing, retrieval APIs, and agent integrations. The role requires production software experience, cloud-native development, LLM and generative AI expertise, and strong ownership in an ambiguous early-stage environment.
About the job
Responsibilities
- Build, test, and operate backend services for context ingestion, indexing, retrieval orchestration, API access, source configuration, and system administration.
- Define and build a scalable multi-tenant SaaS foundation, including tenant isolation, usage tracking, quotas, audit logs, background jobs, and reliable service boundaries.
- Build APIs and service interfaces for AI agents, MCP tools, CLIs, and internal applications to retrieve context, provenance, confidence signals, and warnings.
- Balance fast experimentation with long-term reliability as the project moves from prototype to production.
- Instrument services with metrics, logs, traces, alerts, and dashboards; use observability tools to improve reliability.
- Contribute to architecture, service boundaries, storage choices, API contracts, deployment patterns, and engineering practices.
- Communicate effectively and collaborate across teams.
- Own AI solutions through scalable, maintainable implementation aligned with user workflows.
Requirements
- Experience with LLMs, prompt engineering, and applications powered by generative AI.
- Proven experience delivering production software actively used by users.
- Experience in cloud-native environments such as AWS, GCP, or Azure.
- Experience using observability tools to understand and troubleshoot system behavior.
- Strong engineering skills building production-grade, user-facing software systems.
- Familiarity with AI technologies and frameworks, with a practical delivery mindset.
- Ability to iterate quickly, release prototypes, collect feedback, and refine solutions.
- Initiative, ownership, and comfort working through ambiguity.
- Effective collaboration and communication skills.
Nice to Have
- Experience with agent frameworks or multi-agent workflows.
- Experience as a data analyst or with data platforms such as Looker, Tableau, Power BI, Snowflake, or Databricks.
- Experience building tools for data engineering.
Compensation and Benefits
- Base compensation in Canada: CAD $186,368–$223,642.
- Compensation may vary based on level, experience, and skill set.
- Benefits include equity, bonus where applicable, and other company benefits.
- 100% remote work, global collaboration, career growth opportunities, and an open-source, high-trust culture.
Skills
LLMs, Prompt Engineering, Generative AI, AWS, GCP, Azure, Observability, Mcp, Agent Frameworks, Multi-Agent Workflows, Snowflake, Databricks, API Design, Multi-Tenant Saas, Background Jobs
Similar jobs
Backend Engineering jobsStaff Backend Engineer responsible for evolving Grafana into a scalable, multi-tenant observability application platform. The role requires production SaaS experience, distributed-systems expertise, strong backend coding skills, and familiarity with or willingness to learn Golang.
Build large-scale backend infrastructure and data products for Databricks across areas such as log analytics, AI/BI, business semantics, and apps. The role requires staff-level software engineering experience, including 10+ years with Java, Scala, or C++ and expertise in distributed systems and cloud technologies.
Leads the technical vision and architecture for large-scale backend systems powering experimentation, personalization, analytics, and conversion optimization. The role requires 12+ years of software engineering experience, deep distributed-systems expertise, and cross-functional technical leadership.
Leads development of reliable, scalable database connectors and replication technology for enterprise data movement. The role requires strong Java or C/C++ experience, database internals expertise, distributed-systems design skills, and technical leadership through architecture, mentoring, and production investigations.
Technical leader for the Metadata team, designing distributed cloud subsystems and leading complex initiatives across discovery, catalog, lineage, and run history services. Requires 8+ years of software engineering experience, backend or systems expertise, cloud infrastructure experience, and strong architecture, reliability, and mentoring skills.