[Remote] Staff AI Engineer

Note: The job is a remote job and is open to candidates in USA. TaskRay is a leader in post-sale work management in the Salesforce ecosystem, focused on enhancing customer experiences. The Staff AI Engineer will lead the technical design of TaskRay's AI platform, overseeing architecture, engineering standards, and engagement with design partner customers to build innovative AI solutions.ResponsibilitiesOwn the architecture of TaskRay's off-platform AI tier, including the contracts that connect it to our Salesforce-native coreMake and defend build versus buy decisions across the agent stack: orchestration, retrieval, evaluation, observability, and guardrailsPartner with our Architect and Senior Salesforce Engineering Lead on the data contract between the Salesforce platform and the off-platform AI layerTranslate the company's AI strategy into a buildable technical planArchitect and lead the build of our MCP server, the platform layer that connects agents to TaskRay's project, customer, and onboarding data and gives us control over usage analytics, packaging, and external agent connectionsDesign and lead the build of our PM Agent, an internal-facing agent that materially increases customer team productivity by maintaining live project status and surfacing the next best actionDesign and lead the build of our Execution Agent, an internal-facing agent that completes tasks on behalf of human counterparts inside TaskRay workflowsDesign and lead the build of our External Onboarding Agent, the customer-facing agent that handles status updates, document collection, and end-customer interaction across the onboarding lifecycleBuild the eval, observability, and feedback infrastructure that lets us iterate on agents safely against real customer dataSet our approach to retrieval, tool use, and multi-step reasoning. We expect production-quality systems, not demo-qualityPartner with our design partner customers (3 to 5 in the first phase) to discover the repeatable workflow patterns worth productizing across the PM Agent, Execution Agent, and External Onboarding AgentLead the technical scoping for design partner work: what we build custom, what we build into the core product, what we deliberately do not buildBe the technical voice in those engagements alongside Product. Engagements run via video and shared tooling, not on-siteEstablish TaskRay's engineering standards for AI feature development: prompt iteration, eval-driven workflows, agent observability, cost and latency budgets, security and compliance postureActively contribute to our agentic coding standards and normsMentor senior and mid-level engineers contributing to AI work, and shape the broader hiring bar for AI capability on the teamSkillsTrack record of shipping production agent systems at meaningful scale (real users, real reliability requirements, real failure modes you have debugged)Deep, hands-on experience designing agent systems in production: tool use, multi-step reasoning, retrieval pipelines, and the evals required to iterate on them safelyStrong Python proficiency (the lingua franca of the AI stack), with production experience deploying real systemsHands-on experience with Anthropic Claude or comparable LLM provider APIs at production scale, including reliability patterns, eval harnesses, and cost and latency engineeringDemonstrated technical leadership: scoping work for multiple engineers, making and defending architectural decisions, and partnering credibly with senior stakeholders. We are level-agnostic on years; we care about the workComfort in customer-facing technical discovery and design partner contexts. You can listen well, scope tightly, and hold your own with a senior buyerExperience with Model Context Protocol (MCP), agent orchestration frameworks, or comparable toolingExperience operating in compound or agentic development workflows (Claude Code, Cursor, or equivalent), with a point of view on how teams should adopt themBackground that includes one or more of: customer-embedded technical engagements, ML platform, or research-to-production transitionsBenefitsBonus based on company and individual performance targetsMedical, dental, and vision benefitsEvery other Friday off and a team that respects your time outside of workFlexible PTO12 weeks paid family and medical leave, 16 weeks for birthing peopleVacation bonusesAnniversary bonusesCompany-paid life insurance401(k) matchingCell phone reimbursement stipendEmployee Assistance ProgramCompany OverviewTaskRay is the solution for on boarding customers at scale in Sales force. It is a sub-organization of Bracket Labs. It was founded in 2010, and is headquartered in Lafayette, Colorado, USA, with a workforce of 51-200 employees. Its website is http://taskray.com.