• This is a remote role.

Role Description Build agents for the entertainment industry and creator economy. We are hiring an Applied AI Engineer dedicated to agent reliability. The mandate is deliberately narrow. We don't need another full-stack engineer or a generic senior architect. We need someone whose hands stay in the eval pipeline and who turns the multi-agent system from "works in demos" into "survives non-deterministic LLM output at production scale." You will partner with the technical co-founder on architecture decisions where reliability is at stake, including HITL escalation, thread context collapse, and multi-channel routing. The team owns the long-term evals vision, and this hire builds and runs the pipeline day-to-day. What You'll Own - Instrument the scheduling agent end-to-end with traces on top of the existing Langfuse deployment - Build eval datasets from real production traffic across the agent layer (scheduling, notetaker, iMessage, Gmail) - Stand up the Braintrust scoring pipeline, including both quality scorers and robustness scorers (did the system survive the LLM output, did HITL trigger when it should) - Own the feedback loop from evals to prompt and architecture changes to re-evaluation, including DSPy and DPO as the system matures - Partner with the technical co-founder on agent architecture decisions where reliability is at stake - Operate end-to-end on your workstream: dev, test, deploy, and on-call sustain Qualifications - Real production experience with non-deterministic LLM systems. Evidence of shipping, debugging, and maintaining agent systems under real traffic (not side projects or OpenAI API experimentation) - Has built or operated an eval pipeline before. If not Braintrust specifically, the intuition for scorer design has to be there - Product-first mindset applied to evals. Can take scorer design and feedback loops and drive a real product forward (not just build models in isolation) - Strong Python backend fluency. The stack is FastAPI, Django, Celery, and LangGraph - Comfortable with observability tooling (Langfuse or equivalent) and logs/metrics stacks like Grafana or Loki - Senior enough to own a workstream end-to-end from dev to test to deploy to on-call sustain (no pair programming crutch) - Works async, writes clearly, fluent English Requirements - DSPy, DPO, or other LLM optimization experience - Prior agentic systems work with LangGraph or similar (tool use, planning, multi-step) - Time at a prestige-tier LATAM company (Nubank, Itaú, iFood) or strong YC/US startup - Exposure to multi-model stacks (GPT-4.1/4o, Claude, Whisper) in production Benefits - Salary: $84,000 - $120,000 per year - Experience: 3+ years - Stage: Pre-seed Company Description Building agents for the global entertainment industry and creator economy. Professionals at WME, UTA, Netflix, Night, and Live Nation use this product today through private beta. The company has a massive trust moat: a 270K+ proprietary distribution network of verified entertainment professionals. Founded by Vince Morales (2x founder, UTA Ventures, Elevate Ventures), Warner Bailey (2x founder, WME, Live Nation), and Ryan McCaffrey (WMG, Hebbia AI, Robinhood). Technical talent from NVIDIA, Intuit, and HubSpot. Oversubscribed its $400K round through angels from Coatue, Ramp, Plug and Play, FanFix, Temple Hill, Outshine Talent, and Undercurrent Talent. Now raising $2M with +$500K already committed.

• Own and ship internal automation roadmap • Build production systems on top of AI models • Collaborate directly with engineering and delivery leadership • Turn documented automation workflows into shipped, working systems

Role Description The Prompt + Skills Engineer is the hands-on builder in Cherry Bekaert’s AI Center of Excellence — the person who writes the prompts, builds the skills and ships the workflow components that 3,000 professionals across Tax, Assurance, Advisory and Wealth Management use to deliver client work. Working under the direction of the AI Workflow Architect, this role turns architectural designs into production-ready tools that work reliably at scale. - Writes, tests and refines prompts across Tax, Assurance, Advisory and Wealth Management use cases, following the architectural standards and prompt patterns established by the Workflow Architect. - Builds, maintains and versions Claude skills and workflow components, managing the full lifecycle from development through testing to production deployment. - Curates and organizes the Firm’s prompt library, tagging entries by service line, use case type, complexity tier and validation status to maximize discoverability and reuse across teams. - Conducts quality assurance testing on AI outputs, including accuracy validation, edge case testing, hallucination detection and compliance checks against the Firm’s professional standards. - Supports the Ambassador network by providing hands-on technical assistance, troubleshooting workflow issues and delivering implementation guidance when new tools and skills launch. - Documents prompt engineering patterns, skill specifications and build processes in the CoE knowledge base, creating the reference material that enables the team to scale. - Collaborates with service line professionals and subject matter advisors to capture domain-specific requirements and translate them into prompts and skills that reflect how work actually gets done. - Participates in use case intake, evaluating submitted ideas from across the Firm for technical feasibility, effort estimate and alignment with the existing production roadmap. - Monitors AI platform updates and new capabilities (e.g., Anthropic Claude releases, new tool-use and agentic features) and assesses their impact on existing skills and workflows. - Contributes to the Firm’s AI training materials by developing prompt examples, live skill demonstrations and technical reference guides that the Coordination Track uses for Ambassador enablement. Qualifications - Bachelor’s Degree in Computer Science, Data Science, Information Systems, Engineering or a related field. Relevant certifications in AI/ML platforms (e.g., Anthropic, Microsoft AI, AWS ML) are a plus. - Hands-on proficiency in prompt engineering, including the ability to write, test, iterate and optimize prompts for accuracy, consistency and usability — or demonstrated aptitude and eagerness to develop these skills rapidly. - Familiarity with AI platforms and tools relevant to professional services (e.g., Anthropic Claude, Microsoft Copilot, AI development frameworks) with a clear willingness to develop deep technical capabilities on the job. - Strong process orientation with the ability to follow established architectural standards, maintain version control, execute structured build-test-deploy workflows and keep the prompt library organized. - Analytical mindset with attention to detail, particularly in evaluating AI output quality, identifying patterns in failure modes and conducting systematic, repeatable testing. - Willingness to learn Cherry Bekaert’s Tax, Assurance, Advisory and Wealth Management domains — understanding enough about how professionals work to build prompts and skills that fit their actual workflows. - Strong written communication skills, including the ability to write clear technical documentation, maintain knowledge bases and create training materials that non-technical colleagues can follow. - Collaborative working style suited to a small, cross-functional team, with comfort engaging service line professionals, Ambassadors and technical colleagues across levels. Benefits - Our shared values that foster inclusion and belonging including uncompromising integrity, collaboration, trust, and mutual respect. - The opportunity to innovate and do work that motivates and engages you. - A collaborative environment focused on enabling you to further your career growth and continuous professional development. - Competitive compensation and a total rewards package that focuses on all aspects of your wellbeing. - Flexibility to do impactful work and the time to enjoy your life outside of work. - Opportunities to connect and learn from professionals from different backgrounds and with different cultures.