About the Role

The Senior Research Engineer will lead the development of multimodal large-language foundational models (LLMs) and novel algorithms to advance state-of-the-art AGI. Responsibilities include scaling training on large GPU clusters, optimizing workflows, and building efficient models. This role involves hands-on machine learning, distributed systems, and influencing overall strategy at the intersection of engineering and applied science.

Key Responsibilities

• Lead development of novel algorithms and modeling techniques for multimodal LLMs
• Scale training of models on hyper large GPU and AWS Trainium clusters
• Optimize training workflows using distributed training/parallelism techniques
• Optimize low-level details like CUDA kernels, communication collectives, network I/O
• Utilize and extend industry frameworks (NeMo, Megatron Core, PyTorch, Jax, vLLM, TRT)

Required Skills & Qualifications

Must Have:

• 5+ years of professional software development experience
• 5+ years of programming with at least one software language
• 5+ years of leading design or architecture of systems
• 2+ years of practical machine learning experience

Nice to Have:

• 5+ years of full software development life cycle experience
• Master's degree in machine learning or equivalent
• Hands-on experience training Foundational Models/LLMs or low-level optimization

Benefits & Perks

• Medical, financial, and other benefits
• Equity and sign-on payments may be provided
• Inclusive culture with workplace accommodations