Member of Technical Staff - Post Training, Applied (Vision)

What you'll do

• Own customer VLM post-training engagements and translate requirements into specifications and workflows.
• Design visual data generation, filtering, curation, annotation, and quality assessment processes; run SFT, preference alignment, and reinforcement learning workflows.
• Build task-specific evaluations for visual understanding, grounding, OCR, document parsing, and other multimodal capabilities, and feed findings into core pipelines.

What they ask for

• Hands-on experience with data generation and evaluation for VLM or multimodal post-training.
• Experience training or fine-tuning vision-language models using SFT, preference alignment, and/or RL.
• Strong intuition for visual data quality, annotation design, and multimodal evaluation.
• Familiarity with vision encoders, image-text architectures, and interactions between visual representations and language model backbones.

Nice to have

• Experience with visual grounding, document understanding, OCR, or video understanding tasks.
• Experience contributing to shared or general-purpose multimodal post-training infrastructure.

Tools

VLM, SFT, RL

AI focus

Applied post-training, evaluation, and deployment of vision-language models, with applied learnings feeding into general-purpose multimodal model development.