Devops + ML Engineer | 8Yr Exp req

Position: MLOps Engineer

Level: Senior

Experience: 8 10 years

Location: Noida (hybrid)

Budget: 16-18 LPA

About the role

You own the infrastructure that keeps our AI products running - and running accurately - long after launch. This is a combined DevOps + MLOps role because the two disciplines now overlap heavily in production AI systems, and we'd rather have engineers who think across both than two silos that hand work over a wall.

You build the CI/CD pipelines, manage the cloud infrastructure, and operate the model lifecycle: deployment, monitoring, drift detection, retraining, and rollback. Our commercial model includes keeping client AI systems from silently degrading the 10 15% that unmonitored chatbots typically drop within months of launch.

This is a production-first role. If something breaks in a BFSI client's loan workflow at 2am, you're the person who finds out before they do.

Required qualifications

• 8 10 years in DevOps, SRE, or platform engineering, with the last 2+ years operating production ML or LLM systems (not just shipping models from notebooks to a REST endpoint).
• Strong Python (for tooling and pipeline code) and strong Bash. Working knowledge of Go or one statically-typed language is a plus.
• Production experience with at least one managed ML platform - AWS SageMaker, Azure ML, or Google Vertex AI - including endpoints, pipelines, and model registries.
• Production experience with Kubernetes and Terraform (or equivalent IaC).
• Hands-on experience with at least one CI/CD platform - GitHub Actions, GitLab CI, Jenkins, CircleCI, Argo CD.
• Demonstrable experience with observability tooling - Prometheus/Grafana, Datadog, CloudWatch, or the equivalent on Azure/GCP.
• Hands-on experience with drift detection and model monitoring - Evidently, WhyLabs, Arize, Fiddler, or a custom-built equivalent you can speak to in detail.
• Solid grasp of cloud cost optimisation - you've actually cut cloud bills, not just talked about it.

Preferred qualifications

• LLM-specific observability experience - LangSmith, LangFuse, Helicone, Arize Phoenix, or equivalent.
• Experience deploying and operating open-source LLMs on private infrastructure - Llama 3, Mistral, vLLM, TGI, Ollama, on bare metal or VPC.
• GPU infrastructure experience - provisioning, scheduling, cost management (A100/H100/L4 fleets).
• Experience with feature stores - Feast, Tecton, SageMaker Feature Store.
• Familiarity with DPDP Act 2023, HIPAA, and sector-specific compliance requirements (RBI cybersecurity guidelines, IRDAI, etc.).
• Prior on-call experience for production systems with paying clients.
• Experience supporting consulting or services-led engagement models.