About the Role:

We are looking for a hands-on MLOps Engineer specializing in ML engineering, model deployment, model governance, and observability. The role covers the complete lifecycle of Deep Learning models, LLMs, and SLMs.

Key Responsibilities:

- Build and manage MLOps and LLMOps pipelines.

- Deploy, host, and scale Deep Learning models, LLMs, and SLMs.

- Manage model versioning, deployment, rollout, rollback, and retirement.

- Host models on Databricks, Kubernetes, OpenShift, and GPU infrastructure.

- Implement model governance, lineage, approval workflows, and compliance controls.

- Build monitoring, tracing, logging, and drift-detection capabilities.

- Optimize model latency, throughput, GPU utilization, and cost.

- Support cloud, on-premises, hybrid, and air-gapped environments.

Required Skills:

- 3 - 5 years in MLOps, LLMOps, ML Engineering, or AI Engineering.

- Strong Python.

- Hands-on Databricks and/or Azure ML.

- Experience with Deep Learning, LLMs, SLMs, RAG, and Hugging Face.

- Experience deploying PyTorch and TensorFlow models.

- Strong Kubernetes, Databricks, and GPU deployment experience.

- Experience with vLLM, Triton Inference Server, Ray Serve, SGLang, or Databricks Model Serving.

- Strong NVIDIA GPU and CUDA knowledge.

- Model Registry, Governance, Monitoring, Drift Detection, and AI Observability.

- SQL Server, PostgreSQL, Oracle, MySQL, or MongoDB.

- Vector databases such as Pinecone, Chroma, FAISS, Milvus, or Azure AI Search.

- REST APIs, WebSockets, and Streaming HTTP.

- MLflow, OpenTelemetry, LangFuse, Splunk, and Grafana/ELK.

- Jenkins and Azure DevOps.

- Keycloak/authentication setup experience.