Sarvam
ML Ops Engineer, Chanakya
Delhi. Posted 7 months ago
The role
The MLOps Engineer owns the model lifecycle for defence and strategic sector deployments. This includes serving infrastructure, monitoring, evaluation pipelines, and environment management.
What you will do
- Design and operate model serving infrastructure across on-prem and cloud deployments
- Build and maintain CI/CD pipelines for model updates, rollbacks, and evaluation-gated deployments
- Monitor model performance in production
- Build evaluation infrastructure including harnesses, A/B testing, and model comparison tooling
- Manage containerised model serving in constrained, air-gapped, and edge environments
- Collaborate with Data Scientists on eval pipelines
- Create runbooks and operational playbooks for Strategic Deployment Engineers
- Own incident response for model-layer failures across all active deployments
Required qualifications
- 3–5 years in ML engineering or MLOps with at least one production LLM or ML system in continuous operation
- Deep expertise in model serving: vLLM, TGI, Triton Inference Server, or equivalent
- Experience with quantised model formats (GGUF, AWQ, GPTQ)
- Experience fine-tuning and adapting models in constrained, on-prem, or air-gapped environments
- Experience managing data pipelines and compute limitations specific to the environment
- Containerisation experience with Docker, Kubernetes, or lightweight alternatives (K3s, K0s)
- Familiarity with deploying across heterogeneous hardware and infrastructure configurations
- Monitoring and observability using Prometheus, Grafana, or equivalent
- Ability to build custom eval dashboards
- Python fluency
- Familiarity with fine-tuning workflows and model evaluation frameworks
- Hands-on experience with CI/CD tooling for ML pipelines: GitHub Actions, ArgoCD, DVC, or similar
About the company
Sarvam is building the bedrock of Sovereign AI for India by developing a full-stack sovereign AI platform. The company works with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures.