27 days ago
India (city not specified)Staff+
Responsibilities
- Architect and build production-grade multi-step, tool-using agentic systems with orchestration, planning, memory, context management, and human-in-the-loop controls.
- Develop shared AI platform capabilities including reusable agent frameworks, tool and MCP integrations, LLM gateways, prompt and model versioning, and evaluation infrastructure.
- Build AI observability and evaluation systems covering tracing, quality, latency, cost, safety, offline evaluations, regression suites, and production monitoring.
- Provision, scale, secure, and optimize cloud infrastructure for AI workloads across GCP and AWS, including inference and token-spend governance.
- Establish reliability and safety practices including guardrails, scoped permissions, sandboxing, prompt-injection defenses, audit trails, graceful degradation, and incident management.
- Set technical direction, lead design reviews, write and review code, mentor engineers, and drive adoption of AI-first engineering practices.
- Partner with product engineering, SRE/infra, security, and leadership teams to align platform capabilities and communicate technical direction, risks, and progress.
- Drive measurable optimization of inference, token, and infrastructure costs while maintaining quality and reliability.
Requirements
- 12+ years of overall software engineering experience, including significant time as a senior or staff-level individual contributor.
- At least one year architecting production agentic systems, including multi-step tool-using agents, orchestration, memory and context management, and guardrails.
- Expert-level proficiency in Go, Python, or Node.js.
- Hands-on experience writing and reviewing code, debugging production issues, and working deeply with architecture; purely managerial experience in the last year is not sufficient.
- Strong knowledge of LLM application fundamentals including tool/function calling, MCP, retrieval, context engineering, prompt and model management, and evaluation methodologies for non-deterministic systems.
- Strong AI observability experience using tools such as Prometheus, Grafana, ELK, OpenSearch, or equivalent.
- Strong understanding of distributed systems architecture, including consistency, availability, fault tolerance, scaling patterns, and trade-offs.
- Demonstrated enterprise cloud cost optimization, including LLM inference and token-spend management through routing, caching, and budgets.
- Practical experience managing GCP and/or AWS services, including provisioning, scaling, IAM, networking, and cost governance.
- At least three years of individual contributor experience on enterprise-scale platform teams.
- Ability to lead technically without authority through design documentation, cross-team alignment, and mentoring.
- Data-driven decision-making and strong verbal and written communication skills for technical and non-technical stakeholders.
- Open-source contributions or published work on agentic systems are preferred.
Benefits
- HighLevel operates as a global, remote-first organization across more than 10 countries.
- The role offers broad technical ownership, hands-on architecture work, and the opportunity to shape AI platform foundations used by teams across the organization.
Tech Stack
Categories
About HighLevel
HighLevel builds a white-label, all-in-one marketing and CRM platform for agencies, entrepreneurs, and SMBs, combining lead capture, automation, email/SMS, websites and funnels, payments, and appointment management. Founded in 2018 and headquartered in Dallas, it is privately held and raised $60M in private equity funding in 2024. The subscription SaaS serves customers in 150+ countries and is used by over one million businesses.