← All roles

Staff Engineer - AI Platform

GoHighLevel· Platform
Apply on company site
RemoteEmployee IndiaPosted 4d ago

About the role

Staff Engineer (AI) to architect and build agentic systems and AI foundations within the Platform Services team, responsible for shared infrastructure, internal tooling, and core services to enable AI-driven capabilities at enterprise scale.

Responsibilities

  • Production-grade agentic systems - multi-step, tool-using agents with orchestration, planning, memory and context management, and human-in-the-loop controls - for platform automation and internal engineering workflows.
  • A shared AI platform for product teams: reusable agent frameworks, tool and MCP integrations, an LLM gateway (routing, rate limiting, caching, fallbacks), and prompt/model versioning.
  • Evaluation and observability for AI systems - eval harnesses, tracing of agent runs, and metrics for quality, latency, cost, and safety.
  • AI-driven engineering practices that improve developer velocity - agentic developer workflows, AI-assisted tooling, and automation of operational toil.
  • Cloud infrastructure for AI workloads across GCP/AWS, including provisioning, scaling, security, and cost governance for inference and token spend.

Qualifications

  • 12+ years of overall software engineering experience, including significant time as a senior or staff-level individual contributor.
  • At least the last 1+ year spent architecting agentic systems in production - designing multi-step, tool-using agents, orchestration, memory and context management, and guardrails, not just integrating LLM APIs.
  • AI-first mindset (must have) - actively using AI tools in your own engineering workflow, with the ability to set and drive an AI-first culture within the Platform Services team.
  • Expert-level proficiency in either Go, Python or Nodejs.
  • Strong hands-on orientation - comfortable writing and reviewing code, debugging production issues, and going deep on architecture.
  • Strong working knowledge of LLM application fundamentals - tool/function calling, MCP, retrieval and context engineering, prompt and model management, and evaluation methodologies for non-deterministic systems.
  • Strong observability fundamentals, with deep experience in AI observability - tracing agent runs and monitoring quality, latency, cost, and safety in production - using tools like Prometheus, Grafana, ELK/OpenSearch, or equivalent.
  • Strong understanding of distributed systems architecture - consistency, availability, fault tolerance, scaling patterns, and trade-offs at scale.
  • Cost-aware by design - track record of measurable cost optimization in an enterprise cloud environment, including managing LLM inference and token spend through model routing, caching, and budgets.
  • Practical experience with GCP and/or AWS service management - provisioning, scaling, IAM, networking, and cost governance.
  • Prior experience working as an individual contributor on platform teams for at least 3+ years, at enterprise scale.
  • Proven ability to lead technically without authority - writing design docs, driving cross-team alignment, and mentoring engineers.
  • A data-driven approach to decision-making, prioritization, and performance reporting.
  • Excellent verbal and written communication skills, with the ability to influence both technical and non-technical stakeholders.
  • Good to have: open-source contributions or published work on agentic systems.

Skills

Required:Agentic system designLLM application fundamentalsObservability for AI systemsDistributed systemsCloud platforms (GCP/AWS)
Last updated Oct 21, 2026. Interested? Apply on the company site.

About GoHighLevel

It's time to take your Agency to the Next Level

HighLevel is the all-in-one sales & marketing platform that agencies can white-label and resell to their clients!

CRMMarketingSalesAutomationWhite Label
Company profileWebsite

More open roles at GoHighLevel