Lead development and management of architecture for chaining LLM agents, tools, models, and workflows. Develop shared Context Graph for persistent awareness across agents and products. Implement context streaming services for real-time user and system awareness. Define telemetry frameworks to monitor agent operations and build feedback loops. Build evaluation frameworks for agent quality and workflow completion. Lead creation of Model Workbench for non-technical users. Oversee MCP servers, tools, agents, and capabilities governance. Drive cross-functional alignment on architecture, standards, and priorities. Define platform standards and governance. Participate in troubleshooting and prototyping using LangSmith and observability tools. Promote rapid prototyping and evidence-based iteration. Requires experience leading complex AI and LLM-related products, strong understanding of agentic systems, context and knowledge architectures, telemetry and observability, organizational alignment, systems thinking, technical proficiency with LangSmith and APIs, problem-solving, prototyping, and communication skills. Benefits include unlimited PTO, medical/dental/vision coverage, employee equity, discounts, wellness classes, and pet insurance. Salary range $185,000 - $205,000. Location: Atlanta, Georgia.
What you'll do
Similar jobs
More roles worth a look
Related opportunities based on specialty and working model so candidates can keep momentum.
Bellevue, United States; Boston, United States; Boulder, United States; Chicago, United States; Denver, United States; Los Angeles, United States; New York, US; San Francisco, United States; San Jose, United States; Seattle, United States; Ventura, United States•14 days ago
Develop and manage architecture for chaining LLM agents, tools, models, and workflows
Lead development of a shared Context Graph for persistent awareness across agents and products
Implement and manage context streaming services for real-time awareness
Define telemetry framework to understand agent operations in production and build feedback loops
Build evaluation frameworks for testing agent quality, reliability, and workflow completion
Lead creation of a Model Workbench for non-technical users to leverage LLMs and workflows
Oversee registration, documentation, governance, and discoverability of MCP servers, tools, agents, and capabilities
Drive cross-functional alignment on agentic architecture, context standards, ownership models, and platform priorities
Define platform standards and governance for agents, tools, context sources, telemetry, and workflows
Participate in troubleshooting and prototyping using LangSmith and observability platforms
Promote culture of rapid prototyping, experimentation, and evidence-based iteration
Requirements
Experience leading complex technical products involving LLMs, AI agents, workflow systems, developer platforms, ML infrastructure, or AI-driven applications
Strong understanding of LLM agents, tool use, orchestration, multi-agent workflows, state management, context management, and architectural patterns for agentic systems at scale
Experience designing or working with context graphs, knowledge graphs, semantic systems, memory architectures, metadata platforms
Strong understanding of instrumentation, telemetry, evaluation, and observability for complex software or AI systems
Ability to align senior stakeholders and cross-functional teams around shared technical architecture, product priorities, ownership boundaries, and operating standards
Systems thinking across product experience, model behavior, data, infrastructure, APIs, organizational ownership, and operational processes
Technical proficiency with tools such as LangSmith and experience with APIs, workflow orchestration, LLM agent chaining, MCP, evaluation frameworks, and AI development environments
Ability to troubleshoot ambiguous technical problems, rapidly prototype solutions, and translate experimentation into scalable product and architectural decisions
Excellent communication skills to translate technical concepts into clear product strategies and decisions for technical and non-technical audiences
