AI Platform Engineer
Granicus
Skill Required
Key highlights
- Requires 3+ years of AI engineering and implementation experience
- Role is remote-first with global team distribution
- Granicus has appeared on the GovTech 100 list for 5 consecutive years
- No degree requirements for most roles at Granicus
- Focuses on building production-grade, reliable AI solutions embedded in core revenue workflows
- AI implementations integrate with Salesforce, Microsoft 365, Azure AI, and Copilot
Role overview
The RevOps AI Engineer designs, builds, evaluates, and operates AI-powered systems that support revenue workflows across Sales, Marketing, Customer Success, Support, and GTM Operations. This role is responsible for turning AI designs and requirements into production-grade, measurable, and reliable AI solutions that deliver demonstrable business impact. Sitting at the intersection of AI engineering, Revenue Operations, and systems delivery, the RevOps AI Engineer partners closely with RevOps AI Product Management, AI Solutions Architects, and GTM stakeholders to implement AI agents, workflows, and automation grounded in trusted data, governed content pipelines, rigorous evaluation frameworks, and continuous post-launch measurement. The role is ideal for an engineer who values reliability, quality, and outcomes over experimentation, and who can operate AI systems as durable operational capabilities embedded in core revenue workflows.
Responsibilities
- Build, test, deploy, and operate AI-powered workflows, agents, and automations embedded within core RevOps systems (e.g., Salesforce, Microsoft 365, Azure AI & Copilot surfaces)
- Implement prompt logic, orchestration flows, tool calling, and context-retrieval mechanisms for LLM-based systems
- Partner with AI Solutions Architects to translate approved solution designs into scalable, maintainable, and secure implementations
- Ensure AI solutions are production-ready, observable, resilient, and aligned to defined business outcomes
- Support iterative enhancement cycles based on measured performance and stakeholder feedback
- Design, implement, and maintain LLM evaluation frameworks that assess accuracy, relevance, consistency, and outcome impact
- Implement offline evaluations using curated test datasets, golden answers, and regression test suites
- Implement online evaluations, including user feedback loops, telemetry, and behavioral usage signals
- Define evaluation thresholds, quality gates, and readiness criteria required for launch and scale
- Partner with Product and RevOps leadership to ensure evaluation results inform release decisions, prioritization, and iteration
- Design and implement hallucination-reduction strategies in production systems, including retrieval-augmented generation (RAG) patterns, context filtering, grounding, and citation techniques, and guardrails, validation checks, and response constraints
- Continuously monitor AI outputs, confidence signals, and failure modes in live environments
- Investigate root causes of incorrect or low-confidence outputs and implement corrective improvements
- Contribute to shared standards for explainability, traceability, and user trust in AI-assisted workflows
- Define and instrument metrics for AI systems, focused on outcomes rather than feature delivery
- Track model and workflow performance across quality, adoption, latency, and reliability dimensions
- Build telemetry that connects AI usage to downstream operational and revenue impact (e.g., cycle time reduction, capacity unlocked, risk reduced)
- Partner with analytics teams to ensure AI metrics are trustworthy, interpretable, and consistently applied across initiatives
- Support post-launch measurement to validate realized impact within defined timeframes
- Implement context pipelines that draw from structured data, documents, and governed knowledge assets
- Support enterprise content readiness by consuming content through standardized pipelines rather than ad hoc document handling
- Enforce data quality, access controls, grounding standards, and versioning in AI workflows
- Support governance requirements including documentation, testing, auditability, and change management
- Ensure compliance with privacy, security, and responsible AI guidelines across all implementations
- Work closely with RevOps AI Product Managers to understand intent, success criteria, adoption goals, and delivery priorities
- Collaborate with AI Solutions Architects, Systems teams, and GTM stakeholders to ensure implementations align with real-world workflows
- Support enablement and adoption efforts by improving system reliability, explainability, and usability
- Participate in reviews and retrospectives to continuously improve delivery quality and operational impact
- Deliver AI-powered solutions that improve how Sales, Marketing, Customer Success, and Revenue Operations teams work by reducing manual effort, accelerating execution, and improving decision quality
- Build, deploy, and support production-grade AI agents, workflows, and automations integrated with platforms such as Salesforce, Microsoft 365, Azure AI, and Copilot
- Contribute to AI systems that are accurate, reliable, secure, and measurable, ensuring users can trust AI-generated outputs in critical business processes
- Develop evaluation and testing capabilities that improve solution quality and help prevent regressions as systems evolve
- Help reduce hallucinations and improve response quality through grounding, retrieval, validation, and guardrail techniques
- Instrument telemetry and measurement frameworks that connect AI usage to operational and revenue outcomes
- Partner with Product Managers, Architects, and GTM stakeholders to translate business requirements into scalable AI solutions that deliver measurable value
- Contribute to the continuous improvement of Granicus' AI capabilities through experimentation, operational excellence, and ongoing optimization after launch
- Preserve the Confidentiality, Integrity, and Availability (CIA) of Granicus information assets in accordance with the company's information security program
- Ensure the data privacy of Granicus employees and customers and their data, and complete all required privacy training in a timely manner per company policies
Requirements
- 3+ years of AI engineering and implementation experience
- Strong software, data, or automation engineering background with experience operating production systems
- Hands-on experience building and operating LLM-based workflows and agents
- Demonstrated experience designing and operating LLM evaluation frameworks
- Experience reducing hallucinations in production AI systems using grounding, validation, and guardrails
- Comfort defining metrics and success measures, not just implementing features
- Strong understanding of retrieval-augmented generation (RAG), prompt design, and context engineering
- Strong analytical mindset with the ability to debug complex AI system behavior
- Clear written and verbal communication skills across technical and non-technical audiences
- Experience in AI engineering, applied machine learning, automation engineering, or related roles
- Experience deploying AI or automation systems into production environments
- Experience working with cross-functional product, operations, and systems teams
- Experience supporting AI quality, reliability, and evaluation in live systems
Nice to have
- Familiarity with offline evaluations using test datasets and regression frameworks
- Familiarity with online evaluations using user feedback, telemetry, and behavioral signals
- Familiarity with RevOps systems such as CRM, GTM tooling, and workflow platforms
- Passion for building AI-powered products that solve real business problems rather than technology for technology's sake
- Experience developing software, automation, data, or AI solutions that operate in production environments
- Hands-on experience with LLMs, AI agents, prompt engineering, orchestration frameworks, retrieval-augmented generation (RAG), or workflow automation
- Strong curiosity and a desire to understand why AI systems succeed, fail, or behave unexpectedly
- An analytical mindset and enjoyment of debugging complex technical problems using data and evidence
- Comfort working across technical and business teams to translate requirements into practical solutions
- A quality-first approach with an appreciation for testing, reliability, observability, security, and governance
- Strong communication skills and the ability to explain complex concepts to both technical and non-technical audiences
- A desire to help shape how AI transforms revenue operations, customer engagement, and go-to-market workflows at scale
Benefits
- Remote-first work environment with a globally distributed workforce
- Employee Resource Groups (ERGs) to encourage diverse employee voices
- "Coffee with Mark" sessions for employees to interact with the CEO on topics including mental health, work-life balance, and current affairs
- Microsoft Teams communities focused on wellness, art, furbabies, family, parenting, and other employee interests
- Regular special guest discussions on issues impacting the employee population
Additional details
- Granicus' core mission is to build, implement, and maintain technology that transforms the Govtech industry by bringing governments and their constituents together, with a focus on equitable and inclusive technology implementations
- Granicus has consistently appeared on the GovTech 100 list over the past 5 years and has been recognized as one of the best companies to work for on BuiltIn
- Over its 25-year history, Granicus has served 5,500 federal, state, and local government agencies and more than 300 million citizen subscribers via its unmatched Subscriber Network
- Granicus provides comprehensive cloud-based solutions for communications, government website design, meeting and agenda management software, records management, and digital services across the U.S., U.K., Australia, New Zealand, and Canada
- Granicus does not have degree requirements for most roles and encourages applicants who do not meet every listed requirement to apply to support its goal of building diverse, inclusive teams
- The role operates in a highly cross-functional environment supporting end-to-end revenue operations, with a core focus on production reliability, measurable impact, and continuous improvement of AI systems
- Granicus is a remote-first company with a globally distributed workforce across the United States, Canada, United Kingdom, India, Armenia, Australia, and New Zealand
- The role was originally posted on Himalayas