Staff Software Engineer, Agentic Analytics

Quick Facts

• Role: Staff Software Engineer, Agentic Analytics (founding lead)

Description

You will own the end-to-end Agentic Analytics system that answers business questions over governed data. The system must provide verifiable answers with evidence (source, query, freshness) and should ask for clarification or decline when evidence is insufficient. You will build production services for agent-facing analytics, design the context layer, and enforce correctness through an evaluation harness and regression testing.

Responsibilities

• Set the architecture from business question → governed query → verifiable, evidence-attached answer
• Design and build agent-facing data tools (e.g., MCP or equivalent), context retrieval, agent skills for analytics, and answer-serving APIs
• Operate the system in production with reliability, latency, cost, security, and observability standards
• Maintain an evaluation bar for releases and decide when a domain is production-ready
• Build and run the evaluation harness (ground-truth sets, held-out cases, abstention/clarification behavior, scoring, error severity, regression tests)
• Engineer the context layer from metric definitions, approved joins, documentation, glossary, and worked examples
• Roll out the system across domains (marketing, revenue, finance, product) one domain at a time with named owners and certified definitions
• Make the solution replicable (tools, templates, evaluations, documentation)
• Hire, lead, and review a small founding team; set technical bar
• Partner with data platform, model evaluation, security, and domain owners

Requirements

• 10+ years building and operating production analytics or software systems; includes technical leadership
• Experience shipping LLM agents to production (tool use, MCP/similar, retrieval/context engineering, guardrails, observability)
• Hands-on agentic analytics experience relied on by real users (e.g., text-to-SQL/QA over semantic layers)
• Strong LLM evaluation expertise (golden sets, result-level comparison, abstention metrics, error taxonomies, CI regression testing)
• Strong Python and SQL; production services and APIs on a major cloud (Google Cloud preferred)
• Data warehouse + modeling fluency (BigQuery/Snowflake, dbt, semantic layers like MetricFlow/LookML/Cube)
• Ability to reason about grain, metric definitions, and approved joins; detect incorrect metrics early
• Experience with identity-aware access for agents and audit trails
• Experience hiring and developing engineers; empathetic leadership
• Excitement for AI and ability to work through ambiguity with clear design/evaluation documentation

Benefits

• Weekly lunch stipend
• Full health and dental benefits with mental health budget
• Retirement benefits (RRSP/401K/pension scheme)
• 100% parental leave top-up for up to 6 months
• Annual enrichment benefits (arts & culture, fitness/wellness, workspace credit)
• Education and learning stipend
• 6 weeks paid vacation
• Travel budget for other offices if remote; annual company offsite
• $500 home office stipend
• Remote-friendly work with multiple global office locations