ML Ops Engineer, Chanakya at Sarvam AI (Delhi)
Job Description
Sarvam AI is hiring an ML Ops Engineer for its Chanakya team in Delhi to own the model lifecycle across its defence and strategic sector deployments, from serving infrastructure and monitoring to evaluation pipelines and environment management, so that systems stay available, accurate and auditable.
At a glance
- Role: ML Ops Engineer, Chanakya
- Location: Delhi
- Experience: 3–5 years in ML engineering or MLOps
- Stack: vLLM, TGI or Triton; Docker, Kubernetes or K3s; Prometheus and Grafana
- Apply: open until filled (re-checked 12 October 2026)
What you will do
- Design and run model-serving infrastructure across on-premise and cloud deployments
- Build CI/CD pipelines for model updates, rollbacks and evaluation-gated releases
- Monitor latency, accuracy drift, throughput and failure modes, and surface problems before clients notice
- Build evaluation infrastructure: harnesses, A/B tests and model comparison tools for field and lab use
- Run containerised model serving in constrained, air-gapped and edge environments
- Write runbooks for field engineers and own incident response for model-layer failures
The posting is blunt about the stakes: here a model failure is an operational risk, not a user-experience glitch. The role supports Strategic Deployment Engineers in the field and also owns model deployment infrastructure for new products built by Sarvam’s product engineering team.
What Sarvam AI is looking for
- 3–5 years in ML engineering or MLOps, with at least one production LLM or ML system in continuous operation
- Deep model-serving expertise with vLLM, TGI, Triton Inference Server or similar, and quantised formats such as GGUF, AWQ and GPTQ
- Fine-tuning and adapting models in constrained, on-premise or air-gapped settings
- Docker, Kubernetes or lightweight options such as K3s or K0s across varied hardware
- Monitoring with Prometheus, Grafana or similar, including custom eval dashboards
- Python fluency, and CI/CD tools for ML such as GitHub Actions, ArgoCD or DVC
Pay and location
Sarvam’s posting does not state a salary. The role is based in Delhi.
How to apply
Apply through the official Sarvam AI job posting. Sarvam AI’s posting does not give a closing date, so the role is open until filled; ResearchJobs.in will re-check this listing on 12 October 2026. Check the posting for location and work-authorisation details before you apply.
See all our artificial intelligence jobs, or browse more research jobs on ResearchJobs.in.
Hiring institution: Sarvam AI
Official advertisement: jobs.ashbyhq.com
How to prepare for this application
- Serving: compare vLLM, TGI and Triton for a quantised model on limited GPUs.
- Air-gapped ops: think through updating a model with no internet access.
- Drift: explain how you would detect accuracy drift without fresh labels.
- Runbooks: bring an example of documentation others actually used.
- Incidents: prepare a story of a production ML failure you debugged.
About Sarvam
Sarvam is building what it calls the bedrock of sovereign AI for India: a full-stack platform spanning research, foundation models, infrastructure and applications, with a focus on making AI work for India's languages and institutions. Headquartered in Bengaluru, it works with leading enterprises and public institutions, is backed by Lightspeed, Peak XV and Khosla Ventures, and partners with brands such as Tata Capital, SBI Life, CRED, IDFC and LIC.
