Lead Automation Analyst

1. Own End-to-End AI Solution Delivery Inside ORA

You take Success problems from idea to production. You design the orchestration, build the sub-agents and skills, wire up the knowledge base, define success metrics and deploy.

• Translate Success problems into AI solution designs — what the agent does, what context it needs, what the success criteria look like

• Build orchestrators and sub-agents inside ORA that route work across the right skills, models and knowledge sources

• Author and maintain the skills, prompts and knowledge base entries that power your solutions

• Design and instrument feedback loops from day one — thumbs up/down, logs, eval signals — so quality is measurable from launch

• Deploy solutions into production inside ORA, monitor for quality drift and iterate based on real advisor and customer signal

2. Design AI Workflows Across the Call Lifecycle

The advisor experience runs from pre-call prep to post-call follow-up. You own the AI workflows across that arc.

• Pre-call briefs: customer context, adoption signals, retention flags, prior-call summaries

• In-call guidance: next-best-action prompts, recommendation flows, real-time troubleshooting context

• Post-call grading and summaries: quality scoring, AI-generated recaps, CRM updates, sentiment signals

• Transcription-driven follow-ups: customer updates, recap notes, task creation, escalation routing

• Internal knowledge tools: SOP lookup, policy access, product-knowledge retrieval for advisors

3. Partner with RevOps on ORA Platform Capabilities

When a solution requires ORA itself to do something new, you make the case and stay close to the build.

• Identify the platform capability gap — what ORA needs to do for your solution to ship

• Request the feature from RevOps with clear requirements, acceptance criteria, edge cases and customer impact

• Participate in design reviews, give technical input and validate the build against your use case

• Integrate the new capability into your solution once it ships and report back on outcomes

4. Close the Loop with QA II and Success Leadership

You are the build counterpart to QA II’s evaluation work. Together you set the quality bar and the build pipeline.

• Ingest evaluation signal from the Quality Analyst II — what is breaking, what is drifting, what needs to be designed differently

• Prioritize fixes and new builds based on impact, evaluation data and Success leadership input

• Communicate what you shipped and why to Success leadership and Enablement

• Provide design context to QA II so new solutions can be evaluated effectively from day one

5. Raise the Technical Bar Inside the Function

You are the senior technical voice in this function. You shape how AI work gets built here.

• Define and document the patterns for how AI solutions get designed, tested and shipped inside ORA

• Build the playbooks that make the next hire’s onboarding faster

• Set the bar for solution quality, test coverage and observability before anything ships to advisors

• Bring rigor to model selection, orchestration patterns and prompt architecture across the function

6. Stay Sharp: Learn, Experiment, Share

The AI space moves weekly. We hire people who keep up on their own and bring what they learn back.

• Stay current on LLM behavior, orchestration patterns, model releases and emerging AI tooling

• Run small experiments with new models, techniques or evaluation approaches inside ORA

• Share findings with the broader Success team, the Quality Analyst II and RevOps engineering

• Insatiable curiosity and a self-learning mindset — this is non-negotiable. The AI space changes weekly and we hire people who level up on their own without waiting for permission or perfect instructions.

• 7+ years in AI/ML solution work, technical product, prompt engineering, applied AI, automation engineering or a closely related role where you owned end-to-end delivery. We are hiring for trajectory — strong fundamentals plus a steep growth curve.

• Working fluency with LLM behavior — prompt design, orchestration patterns, model selection trade-offs, common failure modes and evaluation design

• Strong understanding of databases and how data flows between systems

• Reads code fluently enough to understand what is running inside ORA, debug integrations, and have substantive technical conversations with RevOps engineers. You do not need to write production code.

• Demonstrated ability to scope a problem, design a solution, write clear requirements and acceptance criteria, and ship it end-to-end

• Strong written and verbal communication — you can translate a Success problem into an AI solution design and explain it to non-technical stakeholders

• End-to-end ownership mindset — you take a problem from idea to shipped and stay accountable to the outcome

• Bachelor’s degree in a related field, or equivalent practical experience

• Hands-on experience with AI development platforms such as Claude, Cursor or similar tools

• Experience designing orchestration patterns, sub-agent workflows or multi-step AI solutions

• Familiarity with retrieval-augmented generation (RAG), vector databases or knowledge-base architecture

• Familiarity with SQL or similar database querying

• Experience with APIs, webhooks or data integration between systems

• Background in customer success, support, sales enablement or call center environments

• Experience with the HighLevel platform or comparable SaaS products

• Prior experience shipping AI workflows into production environments

• Prior experience writing technical requirements for engineering teams to build against