AI Principal Architect

BayOne Solutions; San Francisco (CA); Remote; USD 180,000 - 240,000; Full time

Job summary

BayOne Solutions seeks an experienced AI Solutions Architect to design and deliver an MVP for an enterprise SaaS platform serving government and public sector clients. You will define AI use cases, architecture, and proofs of concept with a focus on LLMs, MCP, and scalable AI integration.

You will guide distributed teams, select models and tools, and ensure data privacy, security, and governance while driving MVP milestones and demos. Occasional travel to hub sites may be required.

Qualifications

• 8+ years of experience in software engineering or solutions architecture, including 3+ years designing and delivering AI/ML solutions in production.

Responsibilities

• Partner with Product Management to identify and prioritize AI use cases across financials, HR and payroll, procurement, and workforce management.
• Define AI architecture, including model selection, Retrieval-Augmented Generation (RAG), agentic workflows, MCP-based integrations, and platform connectivity.
• Use LLMs and AI coding assistants such as Claude Code, GitHub Copilot, and Cursor for prototyping, development, documentation, and code reviews.
• Establish AI-assisted development workflows using coding assistants, MCP servers, and agents for testing, documentation, and code review.
• Build rapid proofs of concept to validate AI features before full-scale development.
• Guide local and offshore engineering teams in designing, developing, testing, and delivering AI capabilities.
• Select appropriate AI models, frameworks, tools, and cloud services while balancing performance, cost, and delivery timelines.
• Define and implement evaluation methods for AI accuracy, latency, cost, and reliability.
• Ensure AI solutions address data privacy, security, auditability, explainability, and responsible AI requirements.
• Drive AI features toward MVP completion and successful demonstration milestones.
• Participate in occasional in-person planning and demo sessions at the designated hub.

Skills

AI/ML architecture

Python

Cloud/AWS/GCP

Team leadership

Stakeholder collaboration

Tools

Claude Code

GitHub Copilot

Cursor

MCP servers

LangChain

LangGraph

LlamaIndex

OpenAI SDKs

AWS Bedrock

Vertex AI

Job description

Location: Remote – Pacific Time Zone (Preference for San Francisco, Los Angeles, or Seattle metro areas; occasional travel to the local hub required)

Engagement: Long Term Contract

Domain: Enterprise SaaS / Public Sector

Job Summary

We are looking for an experienced AI Solutions Architect to help design and develop a new MVP for an enterprise SaaS platform serving government and public sector organizations. The platform will support financials, HR and payroll, procurement, and workforce management.

The ideal candidate will make AI a core part of the product from day one, partnering with Product and Engineering teams to define AI use cases, design scalable AI architecture, build proofs of concept, and deliver demonstrable AI capabilities by the MVP milestone. This role requires hands‑on experience with LLMs, AI frameworks, Model Context Protocol (MCP), and AI‑assisted development tools.

Key Responsibilities

• Partner with Product Management to identify and prioritize AI use cases across financials, HR and payroll, procurement, and workforce management.
• Define AI architecture, including model selection, Retrieval‑Augmented Generation (RAG), agentic workflows, MCP‑based integrations, and platform connectivity.
• Use LLMs and AI coding assistants such as Claude Code, GitHub Copilot, and Cursor for prototyping, development, documentation, and code reviews.
• Establish AI‑assisted development workflows using coding assistants, MCP servers, and agents for testing, documentation, and code review.
• Build rapid proofs of concept to validate AI features before full‑scale development.
• Guide local and offshore engineering teams in designing, developing, testing, and delivering AI capabilities.
• Select appropriate AI models, frameworks, tools, and cloud services while balancing performance, cost, and delivery timelines.
• Define and implement evaluation methods for AI accuracy, latency, cost, and reliability.
• Ensure AI solutions address data privacy, security, auditability, explainability, and responsible AI requirements.
• Drive AI features toward MVP completion and successful demonstration milestones.
• Participate in occasional in‑person planning and demo sessions at the designated hub.

Required Qualifications

• 8+ years of experience in software engineering or solutions architecture, including 3+ years designing and delivering AI/ML solutions in production.
• Hands‑on experience delivering LLM‑based features such as RAG, AI agents, copilots, and document AI in SaaS products.
• Daily, hands‑on experience with AI developer tools such as Claude Code, GitHub Copilot, or Cursor, with examples of improved development productivity.
• Working knowledge of Model Context Protocol (MCP), including building or configuring MCP servers to integrate models with tools, APIs, and data.
• Strong knowledge of major AI model providers, including Anthropic Claude, OpenAI, Gemini, and open‑source models.
• Experience with AI frameworks such as LangChain, LangGraph, LlamaIndex, Claude Agent SDK, or OpenAI Agents SDK.
• Experience with cloud AI services such as AWS Bedrock, Azure AI Foundry, or Google Vertex AI.
• Proficiency in Python and experience integrating AI services with backend and frontend applications through APIs and microservices.
• Experience developing enterprise SaaS solutions, preferably in ERP, GovTech, HR/HCM, procurement, or financial software.
• Experience taking products from concept to MVP, making scope and technical trade‑offs under tight deadlines.
• Ability to collaborate effectively with distributed and offshore engineering teams.
• Must be based in the continental United States and able to work core Pacific Time hours.
• Willingness to travel occasionally for in‑person meetings and demos. Candidates near San Francisco, Los Angeles, or Seattle are strongly preferred.

Preferred Qualifications

• Experience in public sector, civic tech, or compliance‑heavy enterprise software.
• Familiarity with AI governance and public sector compliance frameworks, including NIST AI RMF, FedRAMP, StateRAMP, or CJIS.
• Experience with AWS AI services such as Bedrock, SageMaker, and Textract.
• Experience with multi‑agent orchestration and AI evaluation or observability tools such as LangSmith and Arize.
• Experience fine‑tuning or deploying smaller models for cost‑sensitive workloads.