About TrueFan AI :

TrueFan AI is an enterprise platform for personalised AI video. Enterprises use it to turn one recording into thousands of video variations, for marketing, sales, customer engagement and internal communications. In 2025 we generated 20M+ videos for 100+ enterprises, more than 15 of them with market caps above $10B. We raised a $10M Series A in June 2026.

About the Role :

More and more clients ask us for content at scale : thousands of unique videos, each generated from the client's own data. No two of these projects are alike, so each one needs a custom agentic pipeline. You'll work directly with clients to build these pipelines and run them in production.

For example :

A client wants a short video for each of its 10,000+ product pages. You build an agent that reads each page and writes a script. It then picks a presenter, storyboards the video, generates the shots, adds voice, music and subtitles, checks the result for quality, and regenerates anything that fails, within a fixed budget and timeline.

Key Responsibilities :

- Turn a client brief into a pipeline design, a cost estimate and a set of sample videos

- Build multi-step agents for scripting, storyboarding and generating consistent shots

- Coordinate several image, video, voice and audio models, with fallbacks when one fails

- Build automated QC that catches bad outputs and regenerates them

- Run batch jobs over tens of thousands of items reliably, keeping cost and time per video in check

- Turn patterns that repeat across projects into reusable platform components

Must-Have Requirements :

- 2.5 - 4 years of software development experience, with strong Python (including async)

- Hands-on experience shipping agentic or multi-step LLM systems to production

- Experience with batch or background processing (Celery, Temporal, Ray or similar)

- A good grasp of reliability : retries, rate limits, and jobs that can be rerun safely

- Comfort working directly with clients

- Hands-on experience with, or at least a solid understanding of, AI video generation models such as Wan, LTX-Video, Omni-Flash, Google Veo, and Seedance.

Good to Have :

- Experience with generative image or video models, TTS or lip-sync

- FFmpeg or programmatic video editing

- Experience building evals or LLM-as-judge quality checks

- Docker, Kubernetes, AWS or GCP

- Have worked with tools like n8n/ComfyUI for building pipelines for rapid iteration