Job description
AI Systems Architect and Builder
Location: Remote – Worldwide
Type of Contract: Full-Time
Salary Range: Market Rate
Language Requirements: Strong Written English
Our client is seeking a skilled AI Systems Architect and Builder with experience designing and deploying production-ready AI systems to join their growing team. You will play a key role in architecting, building, and deploying custom AI solutions from technical specifications while collaborating across multiple client projects. Your work will directly impact client operations by delivering scalable AI applications that solve real-world business challenges across healthcare, hospitality, professional services, e-commerce, and field operations.
Key Responsibilities
Translate written technical specifications into fully deployed AI systems, owning the process from architecture through production handoff.
Design end-to-end system architectures, including data flow, orchestration logic, storage, service boundaries, and failure handling.
Build LLM-powered applications such as conversational agents, Retrieval-Augmented Generation (RAG) systems, structured extraction pipelines, and multi-agent workflows.
Develop voice AI and telephony solutions using platforms such as Retell AI, Twilio, and real-time STT/TTS pipelines.
Design robust prompt architectures, structured outputs, guardrails, and production-ready AI workflows.
Build supporting infrastructure including vector databases, SQL/NoSQL databases, schedulers, queues, and containerized services.
Integrate third-party platforms through REST APIs, OAuth, SDKs, webhooks, and legacy business systems.
Develop data ingestion, transformation, normalization, and enrichment pipelines for production AI systems.
Connect AI applications with CRMs, scheduling platforms, billing systems, practice management software, document repositories, and e-commerce platforms.
Ensure secure credential management, secrets handling, and access control across environments.
Build reliable production systems with logging, monitoring, retries, testing, evaluation frameworks, and observability.
Optimize AI performance, latency, token consumption, and overall system cost efficiency.
Troubleshoot and resolve production issues while performing root cause analysis for live client environments.
Manage multiple concurrent client implementations while providing clear asynchronous progress updates.
Produce technical documentation, architecture diagrams, deployment guides, runbooks, and system handoff documentation.
Must-Have Qualifications
3+ years of experience as an AI Engineer, Systems Architect, Full-Stack Developer, Automation Engineer, or similar role.
Proven experience delivering production-ready AI systems from design through deployment.
Strong Python development skills, including asynchronous programming and maintainable software architecture.
Experience building applications using OpenAI, Anthropic, or similar Large Language Model APIs.
Hands-on experience implementing RAG pipelines, embeddings, vector search, and retrieval optimization.
Experience designing multi-agent workflows, orchestration frameworks, and tool-calling architectures.
Strong knowledge of REST APIs, OAuth, SDK integrations, authentication, pagination, rate limits, retries, and idempotency.
Experience deploying applications using Docker, cloud platforms (GCP or equivalent), CI/CD pipelines, and secrets management.
Solid understanding of SQL, NoSQL databases, JSON transformation, schema design, and data engineering principles.
Experience using Git and following software engineering best practices.
Ability to independently deliver projects from written specifications with minimal supervision.
Strong written English communication skills in an asynchronous remote environment.
Preferred Qualifications
Experience with HIPAA-compliant or other regulated environments.
Experience building Voice AI or conversational telephony systems.
Healthcare integration experience with EHR, practice management, billing, eligibility, or clearinghouse platforms.
Experience with workflow automation tools such as n8n, Make, or Zapier.
Frontend development experience for dashboards and internal business applications.
Experience self-hosting open-source AI infrastructure.
Familiarity with AI observability, evaluation, and monitoring frameworks.
Consulting, agency, or freelance software delivery experience.
Contributions to open-source projects or technical publications.
Experience working within distributed engineering teams.
Technical Environment
Candidates may work with technologies including:
Programming Languages: Python, JavaScript, TypeScript
LLMs & AI: OpenAI, Anthropic, Claude Code, Cursor, RAG, embeddings, vector search, agentic workflows
Voice AI: Retell AI, Twilio, Speech-to-Text (STT), Text-to-Speech (TTS)
Cloud & DevOps: Google Cloud Platform (GCP), Docker, CI/CD, event-driven architectures
Automation: n8n, Make, Zapier
Databases: SQL, NoSQL, pgvector, Pinecone, Qdrant
Integrations: REST APIs, Webhooks, OAuth, SDKs
Compliance Requirements
Candidates must be willing to:
Sign a Non-Disclosure Agreement (NDA), Intellectual Property Assignment Agreement, and Business Associate Agreement (BAA) before accessing client systems.
Work exclusively through company-provided accounts, repositories, credentials, and cloud environments.
Follow strict security protocols for handling confidential client information and Protected Health Information (PHI).
Comply with all confidentiality, security, and intellectual property requirements throughout the engagement.
Tools & Equipment
Our client provides all required software licenses, API credits, cloud infrastructure, AI subscriptions, development tools, and third-party platform access. Candidates are expected to provide their own reliable development computer, stable internet connection, and the flexibility to overlap with Hawaii Standard Time (HST) when project requirements require collaboration.
Originally posted on Himalayas
Who can apply
Eligible countries: United States. Accepted UTC offsets: UTC-10, UTC-9, UTC-8, UTC-7, UTC-6, UTC-5, UTC+14. Review the full description for employer-specific work authorization, residency and schedule requirements.