AI Video Generation Architect

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

📋 Description

• Design and develop the complete video generation pipeline from start to finish.

• Create the generative AI pipeline that converts lesson specifications into storyboards, scene graphs, scripts, and production plans.

• Deliver multiple significant features each week.

• Construct the multi-agent production workflow.

• Engineer the video generation system.

• Develop programmatic motion to facilitate worked examples with narration.

• Execute parallelized rendering using generative video models.

• Establish the ground-truth quality assurance system.

• Design a robust, high-scale media infrastructure.

• Elevate team performance standards.

⛳️ Requirements

• You possess an AI-native mindset.

• You are proficient in continuous multi-session development using Claude Code and/or OpenAI Codex.

• You excel in prompt engineering and context engineering.

• You write Agent Skills similar to how other engineers create unit tests.

• You engage in Spec-Driven Development (using GitHub Spec Kit or an equivalent) as part of your regular workflow.

• You have experience building real backend AI orchestration layers that operate autonomously.

• You think in terms of graphs — with shared state flowing through nodes, conditional edges, interrupts, and circuit breakers.

• You have successfully shipped complex agentic pipelines utilizing LangGraph, Python, and TypeScript, or similar technologies.

• You regard durable execution, structured outputs, human-in-the-loop checkpoints, and provider-agnostic model routing as fundamental design principles.

• You have developed evaluation harnesses, annotated datasets, and versioned prompt chains as essential artifacts.

• You are a skilled programmatic media craftsperson.

• You possess extensive experience with a programmatic animation framework (e.g., Manim, Remotion / Motion Canvas) and a solid understanding of FFmpeg fundamentals: codecs, containers, color, audio streams, and muxing.

• You are knowledgeable about TTS model trade-offs, expressive direction using audio tags and SSML, pronunciation lexicons, forced alignment and word-level timestamps, and loudness standards.

• You can discern pacing issues for a twelve-year-old learner and rectify them within the pipeline rather than the waveform.

• You perceive quality as a quantifiable system.

• You create golden datasets and calibrated judges before scaling up generation.

• You integrate deterministic checks (schemas, layout constraints, symbolic math verification, A/V sync) with LLM- and VLM-as-judge evaluations validated against human labels.

• You recognize subtle errors like an incorrect diagram, mispronounced denominator, or an off-by-one worked example — applying the same scrutiny to agent-generated code, which may appear plausible but isn't always accurate.

• You do not release what you cannot measure.

• You are self-motivated.

• You thrive in small, highly autonomous teams and startups where responsibilities are broad and contexts frequently evolve.

• You communicate clearly.

• You take ownership of a problem from start to finish without waiting for a ticket to prompt your next steps.

• You have a passion for learning.

• You actively leverage the latest advancements in AI to enhance both your own work and that of others.

• You are inspired by MCP's mission and vision, eager to create products for teachers and students.

• You aspire to make a significant impact on the world.

• You are driven to be part of something greater than yourself.

• You believe the highest value of your talent lies in empowering others.

• You are prepared to make a real difference in the lives of educators and young learners.

• You have experience in developing edtech products.

• You have experience managing sensitive and/or confidential data, especially in an educational context (COPPA, CIPA, FERPA, PPRA, SOC 2).

🏝️ Benefits

• Employer-sponsored health insurance through CareFirst BlueCross BlueShield.

• Employer-sponsored dental and vision insurance through MetLife.

• Participation in the Vanguard 403(b) deferred-compensation plan with a 3% employer match.

• Paid Time Off, including vacation/PTO (20 days), paid holidays, paid parental leave, sick and safe paid time off, "Me Days," and the opportunity to earn paid Comp time off.

• Annual budget for MCP-funded Continuous Learning for chosen programs (available after 6 months of continuous full-time employment).

• Access to FSA and Dependent Care FSA.

• Company-paid life insurance coverage equal to 1x salary.

• Access to Wishbone Pet Insurance Benefit.

• Flexibility to work remotely and set your own hours (within reasonable limits).