AI Video Generation Architect

Modern Classrooms Project • Washington, DC

3d • $170,000 - $200,000 • Remote

About The Position

The Modern Classrooms Project (MCP) is seeking an experienced, hands-on, AI-native engineer to build a brand new, state-of-the-art generative pipeline that turns specifications into high-quality instructional videos. This role will own the video render path end to end, from the canonical specification to the final rendered output, creating intuitive, powerful tools that will directly support educators and students every day. The goal is to make high-quality instructional videos accessible to all learners, regardless of experience or background, by automating the time-consuming production process.

Requirements

• AI-native expertise, including continuous multi-session development with Claude Code and/or OpenAI Codex.
• Expertise in prompt engineering and context engineering.
• Ability to write Agent Skills and practice Spec-Driven Development (GitHub Spec Kit or equivalent).
• Experience building real backend AI orchestration layers that run autonomously.
• Proficiency in thinking in graphs (shared state flowing through nodes, conditional edges, interrupts, circuit breakers).
• Shipped non-trivial agentic pipelines using LangGraph, Python, and TypeScript, or equivalent.
• Experience with durable execution, structured outputs, human-in-the-loop checkpoints, and provider-agnostic model routing.
• Experience building evaluation harnesses, annotating datasets, and versioning prompt chains.
• Deep experience with a programmatic animation framework (e.g. Manim, Remotion / Motion Canvas).
• Strong FFmpeg fundamentals (codecs, containers, color, audio streams, muxing).
• Understanding of TTS model trade-offs, expressive direction with audio tags and SSML, pronunciation lexicons, forced alignment and word-level timestamps, and loudness standards.
• Ability to identify and fix pacing issues in narration for educational content.
• Experience building quality as a measurable system, including golden datasets and calibrated judges.
• Ability to combine deterministic checks (schemas, layout constraints, symbolic math verification, A/V sync) with LLM- and VLM-as-judge evaluation validated against human labels.
• Self-directed, thriving in small, high-autonomy teams and startups.
• Ability to write clearly and own problems end-to-end without waiting for explicit direction.
• Actively leveraging the latest developments in AI.
• Motivation by MCP's mission and vision, and eagerness to build teacher- and student-facing products.
• Motivation to be part of something larger than oneself and use talent to empower others.
• Readiness to make a real difference in educators' and young people's lives.

Nice To Haves

• Experience building edtech products.
• Experience handling sensitive and/or confidential data, particularly in an education context (COPPA, CIPA, FERPA, PPRA, SOC 2).

Responsibilities

• Architect the video generation pipeline end to end, designing the gen-AI pipeline that transforms lesson specifications into storyboards, scene graphs, scripts, and production plans.
• Ship multiple substantial features per week by leveraging AI and agentic coding.
• Build the multi-agent production workflow, developing agentic orchestration (LangGraph or equivalent) where an orchestrator delegates to specialist agents.
• Engineer the video generation pipeline, building brand-consistent, design-system-driven video generation from structured content, including layout engines, templates, mathematical typesetting, programmatic diagrams, and text-faithful image generation.
• Design programmatic motion to support worked examples with narration, including kinetic typography, transitions, and animated number lines and area models.
• Run parallelized rendering with generative video models.
• Implement narration with TTS (e.g. ElevenLabs v3 / Gemini-TTS) audio tags and SSML, pronunciation lexicons, consistent voice identities, multi-voice dialogue, multilingual narration, and open license music embeds.
• Build the ground-truth quality system, constructing golden datasets of spec-to-video pairs annotated by educators.
• Implement rubric-based scoring with calibrated LLM- and VLM-as-judge evaluators.
• Symbolically verify every worked example with a computable ground truth verification system.
• Architect resilient, high-scale media infrastructure, designing and scaling the distributed backend across Python and TypeScript.
• Own the systems design and ensure the foundational architecture is ready to scale.
• Review the work of teammates and contractors.
• Collaborate with teammates on architecture and implementation reviews.
• Write PR comments, design docs, and agent skills that make the next person faster.

Benefits

• Salaried position: $170,000-$200,000 gross salary per year
• Employer-sponsored health insurance through CareFirst BlueCross BlueShield
• Employer-sponsored dental and vision insurance through MetLife
• Participation in Vanguard 403(b) deferred-compensation plan with 3% employer match
• Paid Time Off, inclusive of: vacation/PTO (20 days), paid holidays, paid parental leave, sick and safe paid time off, "Me Days", and the ability to earn paid Comp time off
• Annual budget for MCP-funded Continuous Learning for the program(s) you request (available after 6 months of continuous full-time employment)
• FSA and Dependent Care FSA access
• 1x Salary Life Insurance company-paid coverage
• Access to Wishbone Pet Insurance Benefit
• Ability to work remotely and to set your own hours (within reason)

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed