Inference Specialist, Creative Technology - InterPositive
Core
Execute and optimize GPU-based generative AI inference workflows for film and series production, bridging research models with creative output.
Role type
Senior IC machine-learning inference specialist (creative technology)
Builds
Production-ready generative AI outputs (video, image, audio) for Netflix film and series projects
Domain
Entertainment / Generative AI / Post-production
Deliverable
production ML models
Required skills
GPU-based model inference, Python, Linux command-line, deep learning inference concepts, video/image production formats, debugging production runs, job schedulers, cloud GPU environments
Preferred skills
Slurm, distributed multi-GPU runs, multimodal generative AI systems
Technologies
PyTorch, CUDA, ffmpeg, OpenCV, NumPy, safetensors, ProRes, H.264/H.265, EXR, PNG, MP4/MOV
Responsibilities
Operate and support custom generative AI inference workflows across film and series projects; Run, monitor, and troubleshoot GPU-based inference jobs across local workstations, cloud infrastructure, and/or cluster environments; Prepare and validate inputs for model inference including video, image, audio, masks, conditioning assets, prompts, metadata, and configuration files; Tune inference parameters in collaboration with Creative Technology leadership, artists, researchers, and engineers; Debug failed or degraded runs by inspecting logs, outputs, configs, model checkpoints, data shapes, masks, frame ranges, codecs, GPU utilization, and environment issues; Maintain clean, repeatable inference launch workflows including scripts, config templates, run manifests, output naming conventions, and result tracking; Partner with researchers and engineers to test new models, checkpoints, samplers, conditioning methods, and pipeline changes in real production scenarios; Identify friction in inference workflows and drive improvements through tooling, automation, documentation, and better defaults; Support rapid iteration with artists and creative stakeholders by preparing outputs for review, comparing variations, tracking parameters, and surfacing clear recommendations; Own quality control for generated outputs; Help bridge communication between creative, production, research, and engineering teams by explaining technical constraints and creative tradeoffs clearly; Maintain awareness of GPU capacity, queue status, runtime expectations; Contribute to a culture of practical experimentation: move quickly, test carefully, document learnings, and turn one-off fixes into repeatable workflows
Seniority
Senior, hands-on IC