Bold Business logo

AI Automation Engineer & Architect - Remote Full Time

Bold Business Philippines

remotefull-time
Posted Apr 22, 2026

**Role & seniority: ** AI Automation Architect (LLM & Cloud); senior (8+ years software engineering; 3+ years production AI/ML)

**Stack/tools: **

  • Languages: Python (FastAPI preferred), TypeScript/Node.js

  • LLMs/RAG: Vertex AI, Gemini (preferred), OpenAI/Anthropic

  • RAG/vector DB: Pinecone, Weaviate, ChromaDB, pgvector

  • Orchestration/agents: LangChain, LangGraph, LlamaIndex

  • Cloud/infra: AWS (IAM, VPC, ECS/EKS, Lambda, SQS/SNS, RDS, Secrets), GCP (Vertex AI, Cloud Run, Pub/Sub)

  • Data: PostgreSQL (multi-tenant schemas/migrations)

  • DevOps: Terraform, GitHub Actions CI/CD

  • Reliability/ops: observability/logging/model monitoring; event-driven patterns

  • Integrations (examples): Greenhouse, HubSpot, QuickBooks, internal services

  • Top 3 responsibilities:

    • Architect and deploy production-grade RAG pipelines (ingestion, embeddings, retrieval, context strategy)

    • Design and build agentic/multi-step workflow orchestration with state, guardrails, evaluations, hallucination mitigation

    • Build cloud-native, event-driven, multi-tenant backend services with secure infrastructure and monitoring

  • Must-have skills:

    • Production RAG (not prototypes), deep vector-search understanding

    • LLM orchestration frameworks (LangChain/LangGraph/LlamaIndex)

    • Strong backend architecture in Python; experience with multi-tenant SaaS

    • Event-driven architecture (retries, DLQs, idempotency) and CI/CD/producti

Full Description

About The Role

We’re hiring an AI Automation Architect (LLM & Cloud) to architect and build the core intelligence layer behind Bold Amplify™. You will design and ship real AI systems used by real customers — not prototypes, not experiments.

This Role Sits At The Intersection Of

LLM systems (RAG, agents, orchestration) Cloud-native multi-tenant SaaS architecture Event-driven backend engineering Intelligent workflow automation Production reliability & observability

If you’ve built production RAG pipelines, deployed LLM-backed services, and care about clean architecture and measurable impact — this role is for you.

What You’ll Own

AI Systems & RAG Architecture

Design and deploy production-grade RAG pipelines using Vertex AI, Gemini, OpenAI, or Anthropic Build embedding and ingestion pipelines for structured and unstructured business data Implement vector search using Pinecone, Weaviate, ChromaDB, or pgvector Architect context management strategies balancing latency, cost, and reliability

Agentic Workflows & Orchestration

Design multi-step agentic workflows using LangChain, LangGraph, or LlamaIndex Build state machines that reason, retain context, and execute business actions Integrate AI agents with systems like Greenhouse, HubSpot, QuickBooks, and internal services Implement guardrails, evaluation pipelines, and hallucination mitigation strategies

Backend & Cloud Architecture

Build scalable backend services using Python (FastAPI preferred) and TypeScript/Node.js Design event-driven systems (SQS/SNS, Pub/Sub, retries, DLQs, idempotency patterns) Architect secure, multi-tenant SaaS infrastructure across AWS and GCP Manage infrastructure as code using Terraform Own CI/CD pipelines with GitHub Actions Implement observability, logging, and model monitoring

Business Translation

Partner with product and leadership to turn operational problems into AI-driven workflows Define measurable success criteria for automation systems Communicate tradeoffs clearly (cost, token usage, reliability, latency)

Who We’re Looking For

You likely match this role if you

Have 8+ years in software engineering Have 3+ years deploying AI/ML systems into production Have built real RAG pipelines (not tutorials) Have implemented LLM orchestration frameworks (LangChain, LangGraph, LlamaIndex) Understand vector databases deeply Have strong Python and backend architecture experience Have worked in multi-tenant SaaS or ERP-like systems Have built event-driven architectures Have owned CI/CD and production reliability Think in systems and workflows — not just models

Required Technical Experience

Python (AI orchestration, data pipelines, backend services) TypeScript / Node.js (API services and integrations) LLM providers (Gemini preferred, OpenAI/Anthropic acceptable) RAG frameworks and retrieval optimization Vector databases (Pinecone, Weaviate, ChromaDB, pgvector) PostgreSQL (multi-tenant schemas, migrations) AWS (IAM, VPC, ECS/EKS, Lambda, SQS/SNS, RDS, Secrets) GCP (Vertex AI, Cloud Run, Pub/Sub) Terraform GitHub Actions CI/CD Event-driven architecture patterns

BONUS

Experience embedding AI into SaaS products LLM evaluation & monitoring pipelines Guardrails and reliability strategies Cost optimization for token-heavy workloads Experience integrating third-party SaaS tools via OAuth & webhooks Frontend familiarity (React/Next.js) for AI UX integration

What Success Looks Like

Within 90 days you will

Ship at least one production-grade RAG workflow Deploy a multi-step agentic workflow tied to a real business function Establish monitoring for latency, cost, and reliability Contribute to scalable AI architecture standards across the platform

About Bold Business

Bold Business is a US-based global business process outsourcing (BPO) firm with over 25 years of experience and $7B+ in client engagements. We help fast-growing companies scale through smart talent strategies, automation, and technology-driven solutions.

Bold Business recruiters always use a “@boldbusiness.com” email address and/or from our Applicant Tracking System, Greenhouse. Any variation of this email domain should be considered suspicious. Additionally, Bold Business recruiters and authorized representatives will never request sensitive information in email or via text.

PythonTypeScriptNode.jsLLM ProvidersRAG FrameworksVector DatabasesPostgreSQLAWSGCPTerraformGitHub ActionsCI/CDEvent-Driven ArchitectureAI OrchestrationData PipelinesBackend Services

Cookies & analytics consent

We serve candidates globally, so we only activate Google Tag Manager and other analytics after you opt in. This keeps us aligned with GDPR/UK DPA, ePrivacy, LGPD, and similar rules. Essential features still run without analytics cookies.

Read how we use data in our Privacy Policy and Terms of Service.