Lead Architect – AI Platform (Bold Amplify™)

Lead Architect – AI Platform (Bold Amplify™)

We’re looking for a Lead Architect to design and build the core systems behind Bold Amplify™, our AI-first operating system for the future of work.

This role sits at the intersection of AI systems, cloud architecture, and real-world business workflows. You’ll architect and build a production-grade, multi-tenant platform where AI intelligence is embedded directly into workflows—not bolted on as a chatbot.

If you enjoy owning complex systems end-to-end, turning messy business data into reliable intelligence, and building platforms that run in production at scale—this role is for you.

This is a hands-on architecture role. You’ll be building real systems used by real customers, not prototypes or experiments.

What You’ll Own

AI Knowledge Platform (“Second Brain”)

• Design and implement a production-ready RAG architecture using Vertex AI, Gemini, and vector databases (Pinecone, Weaviate, ChromaDB)

• Enable AI models to safely and reliably use business data from systems like Greenhouse, HubSpot, and QuickBooks

• Build ingestion pipelines for unstructured data (documents, emails, logs)

Agentic Workflows & Automation

• Design agent-based systems and state machines that reason, retain context, and complete multi-step tasks

• Build AI-driven workflows for use cases like recruiting operations and financial analysis

• Make tradeoffs around latency, cost, context windows, and reliability

Platform & Infrastructure Ownership

• Own the architecture of a cloud-native, multi-tenant SaaS/ERP-style platform

• Design for data isolation, permissions, auditability, and compliance

• Provision and manage infrastructure using Terraform across AWS and GCP

Backend, Integrations & Reliability

• Build backend services using TypeScript/Node.js and Python

• Design event-driven systems with queues, retries, idempotency, and DLQs

• Integrate external systems via REST/GraphQL APIs, OAuth, and webhooks

• Own observability, reliability, and production readiness

Engineering Excellence & GitHub Ownership

• Lead code reviews and enforce PR standards

• Own GitHub repositories and CI/CD pipelines using GitHub Actions

• Implement secure SDLC practices (secrets, environments, branch protection)

• Drive release discipline (versioning, tagging, changelogs)

Business Translation

• Partner closely with product, leadership, and clients

• Translate operational problems into scalable AI architectures with measurable outcomes

• Clearly communicate technical decisions to non-technical stakeholders

Who This Role Is For

• You’re a senior engineer or architect who builds production systems, not experiments

• You’re comfortable owning complex, ambiguous problems end-to-end

• You think in systems and workflows—not just models

• You can balance speed, quality, cost, and reliability in real environments

Requirements (Must-Haves)

• 8+ years professional software engineering experience

• 3–5+ years building cloud-native, multi-tenant SaaS or ERP platforms

• Strong Python (AI logic, orchestration, data workflows)

• Strong TypeScript / Node.js (APIs, integrations, backend services)

• Expert-level SQL/PostgreSQL, including multi-tenant modeling and migrations

• Hands-on experience with event-driven architectures (queues, pub/sub, retries, DLQs)

• Experience integrating external systems via REST/GraphQL, OAuth, and webhooks

• Practical experience deploying LLMs in production (Gemini preferred)

• Experience with RAG frameworks (LangChain, LangGraph, LlamaIndex)

• Deep understanding of token costs, latency, and context tradeoffs

• Expert-level AWS experience (IAM, VPC, Lambda, ECS/EKS, SQS/SNS, EventBridge, RDS, CloudWatch, KMS, Secrets Manager)

• Strong GCP experience, especially Vertex AI and serverless patterns

• Experience with vector databases and unstructured data pipelines

• Expert-level GitHub usage, including GitHub Actions CI/CD

Bonus Points

• Next.js or React familiarity

• Lean, Agile, or TPS exposure

• Client-facing solution architecture or consulting experience

• Experience with ERP, BPO, or large multi-tenant SaaS platforms

What Success Looks Like

• A scalable, reliable AI platform running in production

• AI systems that meaningfully improve real business workflows

• Clean, secure, well-documented infrastructure and repos

• Stakeholders who trust the system—and your technical judgment