About HighLevel:
HighLevel is an AI powered, all-in-one white-label sales & marketing platform that empowers agencies, entrepreneurs, and businesses to elevate their digital presence and drive growth. We are proud to support a global and growing community of over 2 million businesses, comprised of agencies, consultants, and businesses of all sizes and industries. HighLevel empowers users with all the tools needed to capture, nurture, and close new leads into repeat customers. As of mid 2025, HighLevel processes over 4 billion API hits and handles more than 2.5 billion message events every day. Our platform manages over 470 terabytes of data distributed across five databases, operates with a network of over 250 microservices, and supports over 1 million hostnames.
Our People:
With over 1,500 team members across 15+ countries, we operate in a global, remote-first environment. We are building more than software; we are building a global community rooted in creativity, collaboration, and impact. We take pride in cultivating a culture where innovation thrives, ideas are celebrated, and people come first, no matter where they call home.
Our Impact:
As of mid 2025, our platform powers over 1.5 billion messages, helps generate over 200 million leads, and facilitates over 20 million conversations for the more than 2 million businesses we serve each month. Behind those numbers are real people growing their companies, connecting with customers, and making their mark - and we get to help make that happen.
About the Role:
We are building an AI-first scheduling and booking intelligence layer on top of a universal Calendars & Availability Platform. As the Lead Engineer for the Calendar AI Team, you will architect and deliver AI systems that assist users during setup, configuration, and optimization of their booking systems - and evolve this into a full AI-driven scheduling engine that optimizes capacity, utilisation, and resource allocation.
You will lead the design of LLM workflows, RAG pipelines, retrieval layers, embeddings, context builders, scheduling-aware reasoning modules, optimisation algorithms, and backend integrations. You will also guide and mentor engineers as the AI team grows.
This is a deeply technical role with a strong emphasis on AI engineering + System Design + scheduling domain logic.
Responsibilities:
Design and implement LLM-powered onboarding assistants using Google/OpenAI/Anthropic models with deterministic orchestration (LangChain, LlamaIndex, custom pipelines)
Build RAG workflows using vector databases (Pinecone, Weaviate, Qdrant, pgvector) to inject contextual booking data into model prompts
Develop AI-driven configuration engines that translate natural language into structured booking primitives (services, schedules, resources, capacity, pricing rules)
Design optimization models for resource utilization, workload distribution, capacity forecasting, and conflict reduction
Integrate AI pipelines into backend systems using Node.js/TypeScript/Go services
Build scheduling-aware reasoning modules that handle constraints, buffers, lead times, resource availability, and business rules
Create scalable data pipelines for embeddings generation, context indexing, and model fine-tuning/hybrid retrieval
Implement latency-optimized inference orchestration with streaming responses, caching, and hybrid decision engines
Own the AI Runtime Layer enabling vertical-specific booking logic, plugins, actions, and smart suggestions
Lead and mentor the engineering team, enforce architectural standards, and drive long-term AI roadmap
Requirements:
5+ years of backend engineering experience, with at least 2 years building LLM, RAG or intelligent systems
Experience with OpenAI/Anthropic/Google/Meta LLMs (GPT-4+, Claude, Gemini, Llama)
Strong with LangChain, LlamaIndex, or custom LLM orchestration frameworks
Expertise with RAG architectures
Experience building prompt pipelines, tools/agents, and compound reasoning workflows
Comfort with guardrails, validation layers, hallucination reduction, and safety
Strong proficiency in Node.js/TypeScript/Go for platform integration
EEO Statement:
The company is an Equal Opportunity Employer. As an employer subject to affirmative action regulations, we invite you to voluntarily provide the following demographic information. This information is used solely for compliance with government recordkeeping, reporting, and other legal requirements. Providing this information is voluntary and refusal to do so will not affect your application status. This data will be kept separate from your application and will not be used in the hiring decision.
#LI-Remote #LI-HB1
