ML Researcher, Foundational Models
Sarvam AI
Bengaluru, IndiaPosted 3 months ago
S
Skill Required
ModelsMachine Learningrelated fieldbuildingPyTorchdesignGenerative AIAIFulltime
Key highlights
- PhD in Machine Learning, Computer Science, or related field required
- 3+ years post-PhD research experience (or equivalent)
- Hands-on experience pre-training 7B+ parameter transformer models
- High autonomy and compute access for frontier-scale model decisions
- Work with leading Indian enterprises and institutions
- Backed by Lightspeed, Peak XV, and Khosla Ventures
Role overview
Sarvam is building the bedrock of Sovereign AI for India, developing a full-stack sovereign AI platform across research, models, infrastructure, and applications. The company partners with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures. In this role, you will drive open-ended research on architecture, optimization, scaling behavior, training stability, and post-training recipes for next-generation foundational models. This is a hands-on position where you will design and execute ablations at scale, translate findings into production decisions, and collaborate closely with infrastructure and data teams to shape frontier-scale model runs with high autonomy and compute resources.
Responsibilities
- Drive open-ended research on architecture, optimization, scaling behaviour, training stability, and post-training recipes for our next generation of foundational models.
- Design and execute ablations at scales that actually inform large-run decisions — including running pre-training experiments end-to-end yourself.
- Translate research findings into concrete proposals for the next training run, and own those proposals through to production.
- Work shoulder-to-shoulder with the infrastructure and data teams; many of the most important research questions live at that boundary.
- Read broadly, write internally, and publish externally when the work merits it.
Requirements
- PhD in Machine Learning, Computer Science, or a closely related field (or in the final stages of completion).
- 3+ years of research experience post-PhD (or equivalent depth). Exceptional early-career candidates with a strong research record will be considered.
- First-author publications at top-tier ML venues such as NeurIPS, ICML, ICLR, ACL, EMNLP, or COLM.
- Hands-on experience pre-training transformer-based language models from scratch, ideally at 7B+ parameters. You should be able to describe a training run you owned end-to-end, including what went wrong and how you debugged it.
- Meaningful contributions to the open-source LLM ecosystem — research code, model releases, datasets, or substantive contributions to widely-used projects.
- Fluency in PyTorch and comfort with distributed training. You should be able to read a training loop and immediately see where it might be slow, unstable, or wrong.
- Strong intuition for experimental design — knowing what to measure, what to ablate, and what scale a result needs to hold at before it can be trusted.
Nice to have
- Work on novel architectures (mixture-of-experts, state-space models, hybrid architectures) or non-trivial modifications to standard transformers.
- Experience with multilingual or multimodal pre-training.
- Research contributions in post-training (RLHF, RLVR, distillation, reasoning models).
- A track record of taking a research idea from prototype to a capability that shipped.
Benefits
- High ownership and high impact, from day one.
- Work alongside researchers, engineers, builders, and business leaders who move fast and hold each other to a very high bar.
- Everything we do is AI-first, from the way we build and ship to the way we think about problems.
- You can work on problems that could change how an entire country learns, works, and communicates.
Additional details
- You will be one of a small number of people in the world who get to make architectural and training-recipe decisions on a frontier-scale model run, with the autonomy and compute to back it up.
- Sarvam is a fast-moving, high talent-density team building full-stack AI for India, working on problems that push the frontiers of AI with real population-scale impact.
- You will have direct access to large compute and a tight feedback loop with the engineers building our training stack and data pipelines.
- You will be expected to disagree with the team and defend your reasoning with evidence.
- Sarvam partners with India’s leading brands, including Tata Capital, SBI Life, CRED, IDFC, and LIC.
- If you want to work on problems at the frontier of AI in India, Sarvam is the place to be.