Senior Member of Technical Staff, Multimodal AI
Designs and develops cutting-edge multimodal AI systems integrating text, speech, and vision. Conducts research on representation learning using Python, JAX, PyTorch, TensorFlow, with expertise in distributed training and autoregressive models.
About the job
Responsibilities
- Design and develop cutting-edge multimodal AI systems, integrating various modalities such as text, speech, and vision.
- Conduct research and experiments on our advanced compute infrastructure, exploring novel ideas in multimodal representation learning, transfer learning, and more.
- Collaborate closely with our world-class teams, learning from and contributing to their expertise in the field.
Requirements
- Exceptional software engineering skills, with a proven track record of building robust and scalable systems.
- Strong command of Python and popular deep learning frameworks like JAX, PyTorch, and TensorFlow, with understanding of their multimodal capabilities.
- Knowledge of distributed training strategies, especially for large-scale multimodal models.
- Familiarity with autoregressive models, particularly their application in multimodal tasks such as image or video captioning, speech-to-text generation.
Nice-to-Haves
- Publications in top-tier venues demonstrating expertise in multimodal AI research.
- Experience in writing efficient GPU kernels using CUDA, optimising performance for multimodal tasks.
Perks
- Full health and dental benefits, including mental health budget.
- 100% parental leave top-up for up to 6 months.
- 6 weeks of vacation (30 working days).
- Remote-flexible with co-working stipend.
Skills
Python, JAX, PyTorch, TensorFlow, CUDA, Distributed Training, Autoregressive Models, Multimodal Ai
Similar jobs
AI Research jobs
Decagon
San Francisco, CAResearch and build safety models, evaluations, and runtime safeguards for conversational AI agents, addressing prompt injection, unsafe tool use, privacy, and policy risks. Requires 4+ years in AI/ML engineering, research, or safety plus experience deploying and evaluating language models or agentic systems.
Function Health
United States
Evaluates and improves AI-generated clinical outputs, partnering with product and engineering teams to establish safety, accuracy, and clinical-quality standards. Requires an MD, DO, or equivalent clinical doctorate, substantial patient-care experience, strong clinical judgment, and the ability to learn AI evaluation techniques.
Gusto
Denver, COOwns reusable patterns, standards, and tooling for production agentic service workflows, guiding platform priorities, automation measurement, and quality governance. Requires 8+ years in operations, product, or AI, hands-on agentic workflow experience, and strong LLM, metrics, and cross-functional influence skills.
Anthropic
San Francisco, CAApplied AI Research Engineer who tests model capabilities, builds demos and evaluations, supports strategic customer implementations, and translates field insights into product and research direction. Requires 6+ years of technical experience, programming proficiency, LLM development experience, and strong communication skills.
Datadog
Paris, France
The applied scientist will lead GenSim’s methodology for creating realistic, production-grade simulated environments and high-quality post-training data for Datadog agents. The role requires deep LLM and agent experience, evaluation expertise, Python, distributed systems, and the ability to set technical direction.