AI Solutions Architect
Owns reusable patterns, standards, and tooling for production agentic service workflows, guiding platform priorities, automation measurement, and quality governance. Requires 8+ years in operations, product, or AI, hands-on agentic workflow experience, and strong LLM, metrics, and cross-functional influence skills.
About the job
Responsibilities
Build reusable patterns
- Design reusable patterns for agentic service workflows, including orchestration, human-in-the-loop protocols, override and escalation logic, and quality safeguards.
- Establish standards that builders can apply independently.
- Prototype workflows to validate patterns, identify gaps, and unblock difficult problems, then extract reusable capabilities and hand them off.
- Incorporate learnings from each build into shared patterns to improve speed and safety.
Shape the platform
- Influence Product priorities by turning builder friction into specific, evidence-backed requests.
- Prototype capabilities missing from the platform to validate their value before investment.
- Identify gaps between builder needs and existing platform capabilities.
Prioritize opportunities and measurement
- Rank automation opportunities by volume, risk, and customer impact using SOPs, operational metrics, and interaction data.
- Partner with Data to define consistent workflow-performance measurements.
- Identify processes that should not be automated.
Own quality and governance
- Represent customer impact in Legal, Security, Compliance, and platform reviews so requirements are incorporated into reusable patterns.
- Report portfolio performance to senior stakeholders in a concise, action-oriented manner.
Requirements
- 8+ years of experience in operations, product, or AI roles.
- At least 2 years designing and deploying AI-assisted or agentic workflows in production.
- Hands-on experience with agentic tooling, orchestration frameworks, or MCP-style integrations, including multi-agent coordination.
- Strong understanding of LLM systems, prompt design, evaluation, and model behavior at scale.
- Experience designing human-in-the-loop systems with escalation logic, override controls, and compliance-aware checkpoints.
- Ability to define and diagnose workflow metrics, including solve rate, assist rate, containment, and escalation quality.
- Experience influencing Product, Engineering, Legal, Security, and Compliance through writing, design reviews, and high-stakes forums.
- Familiarity with responsible AI, governance, and production risk management.
- Experience working in a function undergoing significant change and building new capabilities in ambiguous environments.
Nice-to-haves
- Experience with retrieval-augmented generation (RAG) architectures and retrieval-quality optimization.
- Ability to assess whether data structures, data quality, and data governance support reliable agentic performance.
- Experience in SaaS, fintech, or regulated environments.
- Exposure to AI governance or safety-oriented review processes.
Compensation
- Denver and most major metro locations: $168,420-$210,525 per year.
- San Francisco and New York: $197,895-$247,369 per year.
- Full-time employees receive benefits and equity.
Skills
Agentic Workflows, Orchestration Frameworks, Mcp Integrations, Multi-Agent Systems, LLMs, Prompt Design, Model Evaluation, Human-In-The-Loop, RAG, Workflow Metrics, Responsible Ai, Ai Governance, Risk Management, Data Governance
Similar jobs
AI Research jobs
Ai2
Seattle, WA
Conduct research and build open foundation models and training systems aimed at accelerating scientific discovery. The role requires a PhD-level background and substantial experience training foundation models, with expertise in agentic training or multimodal data preferred.
Rad AI
United States
Own applied multimodal ML research from clinical problem definition through production, developing and rigorously evaluating computer vision, NLP, and deep learning systems for radiology. Requires strong Python and PyTorch expertise, 4+ years of relevant experience, and an MS, PhD, or equivalent practical experience.
Vanta
Remote
Build Vanta’s organizational intelligence layer by shipping prototypes, internal tools, and AI agent workflows that make cross-source data useful to EPD, GTM, and other teams. The role requires recent hands-on LLM product work, independent problem scoping, and strong judgment around AI quality, reliability, cost, and latency.
Maybern
New York, NY
Build and expand customer-facing agentic AI products, MCP integrations, and automated reconciliation workflows for private fund management. The role requires senior-level software engineering, strong systems thinking, product judgment, and hands-on experience building and evaluating AI systems.
Shield AI
Washington, DC
Conduct field research and human factors analysis with pilots, operators, and customers to shape collaborative work requirements, mission autonomy design, training, and readiness assessments. The role requires human-machine teaming expertise, operational research experience, and comfort working in field and test environments.