Professional Services Technical Operations Engineer – Agentic AI

This is a fully remote position, open to applicants in Texas.

📋 Description

• Spearhead the end-to-end management of agentic AI systems through iterative enhancements, taking ownership of design, security fortification, phased rollout, and continuous upkeep.

• Convert stakeholder needs into precise technical solutions and fluid user experiences, effectively bridging the gap between business and engineering for both technical and non-technical audiences.

• Design multi-agent systems prioritizing interoperability, security, scalability, and cost as critical design factors.

• Establish benchmarks for agent performance, accuracy, cost, and reliability; highlight the key metrics that matter to decision-makers.

• Operate within the sanctioned service portfolio, skillfully navigating approval processes and existing infrastructure instead of defaulting to new proposals.

• Provide strategic counsel to leadership on AI initiatives and roadmaps, mentor team members, and remain updated on advancements in LLMs and agentic frameworks.

• Manage production incident responses across a diverse service portfolio: engage in hands-on troubleshooting, maintain runbooks, and participate in a 24/7 on-call rotation.

⛳️ Requirements

• Proficient in utilizing AI agents to enhance velocity and scope, guiding AI through open-ended, multi-step tasks; adept at implementing adversarial-validation techniques (Challenger agents, confidence scoring, mandatory dissent) to avert LLM groupthink in production environments.

• Demonstrated experience in scaling LLM-based solutions within production settings, with practical knowledge of at least one agentic framework (CrewAI, LangGraph, ADK, or similar) that encompasses agent lifecycle, tool utilization, memory, and orchestration.

• Production-level Python expertise with type hints, testing, and CI/CD practices, increasingly applied in directing and evaluating AI-generated solutions.

• Possess a systems thinking approach and full-stack perspective; understands how changes affect services, data pipelines, frontends, and infrastructure, employing REST APIs, CI/CD, automated testing, and gated rollouts (feature flags, staged UAT) to balance iteration speed with safety.

• Familiarity with AWS in a multi-account production context (SQS/SNS, DynamoDB, S3, IAM); general understanding is sufficient, cloud architect-level expertise is not necessary.

• A genuine commitment to knowledge sharing; considers documentation, runbooks, and architectural decisions as essential deliverables, creating queryable knowledge systems that transform tribal knowledge into a collective understanding.

• Practical delivery in restricted environments; designs solutions around approval constraints and existing infrastructures rather than relying solely on greenfield visions.

• Experience in integrating AI with Slack as a delivery platform (bot frameworks, event subscriptions, slash commands); React/TypeScript frontend experience is appreciated but not mandatory.

🏝️ Benefits

• Market leader in compensation and equity awards.

• Comprehensive physical and mental wellness programs.

• Competitive vacation and holidays for rejuvenation.

• Paid parental and adoption leave.

• Opportunities for professional development for all employees, regardless of level or role.

• Employee Networks, geographic neighborhood groups, and volunteer opportunities to foster connections.

• Dynamic office culture with world-class amenities.

• Great Place to Work Certified™ globally.