Job Description

Senior Research Engineer / Research Scientist – LLM Pretraining

Own the architecture and training of a frontier-scale language model, from first token to flagship run.

Location: Delhi NCR or Bengaluru | Experience: 4 – 12 years

About the opportunity

We are retained by a well-funded AI lab building foundation models from the ground up in India — real compute, real pretraining, not fine-tuning on top of someone else's model. The team is small and the work is unusually direct: what you build ships into the model.

The client's identity is confidential at this stage and will be shared on first call.

What you will do

• Design and implement next-generation model architectures.

• Run rigorous empirical research on scaling laws and training stability.

• Develop and refine large-scale tokenization strategies.

• Act as technical steward for large scout and flagship training runs — continuous uptime, rapid diagnosis of loss spikes and divergence.

What we are looking for

• 4+ years in ML research or software engineering with focused work on LLM pretraining.

• Deep understanding of transformer architectures.

• Hands-on experience training models on large compute clusters.

• Evidence of depth: publications, open-source contributions, or models you have shipped.

What is on offer

• Compensation is open and benchmarked to the top of the Indian market for this profile, with meaningful equity.

• Delhi NCR is the primary base, but the client is flexible on Bengaluru for the right person.

• Relocation support, including for candidates returning from outside India.

How to apply

Apply here, or write to [Confidential Information] with your CV and links to anything you have published, shipped or open-sourced. We reply to every serious application within 48 hours.