JOB ID : QT-SNB-07-324
Job Summary
We are looking for an experienced MLOps Engineer to design, build, deploy, and manage enterprise-grade AI/ML and LLMOps platforms. The ideal candidate will have strong hands-on experience with Python, Databricks, Azure ML, Kubernetes, OpenShift, MLflow, LLM observability, GPU infrastructure, and CI/CD pipelines.
The role involves building scalable ML/GenAI deployment platforms, automating model lifecycle management, implementing monitoring and observability, and establishing robust governance practices for enterprise AI workloads.
Key Responsibilities
- Design, develop, and maintain scalable MLOps and LLMOps platforms for enterprise AI/ML workloads.
- Build and automate end-to-end ML model development, deployment, and lifecycle management pipelines.
- Develop production-grade solutions using Python, Databricks, and Azure Machine Learning.
- Deploy and manage ML/LLM workloads on Kubernetes and OpenShift environments.
- Work with GPU infrastructure for training, fine-tuning, and inference of large AI/ML models.
- Implement model tracking, versioning, experimentation, and deployment workflows using MLflow.
- Build and manage LLM observability and tracing using tools such as LangFuse and OpenTelemetry.
- Design and integrate vector databases such as Pinecone, FAISS, Chroma, or Milvus for RAG and GenAI applications.
- Support deployment and optimization of models using Hugging Face, PyTorch, and TensorFlow.
- Develop and maintain automated CI/CD pipelines using Jenkins and Azure DevOps.
- Implement model monitoring for performance, accuracy, drift, latency, resource utilization, and reliability.
- Establish AI/ML model governance, version control, auditability, security, and compliance practices.
- Collaborate with Data Scientists, ML Engineers, AI Engineers, DevOps Engineers, and application teams to productionize AI solutions.
- Optimize infrastructure and model-serving environments for scalability, performance, reliability, and cost efficiency.
- Troubleshoot production issues across ML pipelines, model serving, Kubernetes, GPU infrastructure, and cloud environments.
- Define best practices for LLM deployment, prompt/version management, evaluation, tracing, and observability.
Required Skills & Experience
- 5+ years of experience in MLOps, ML Engineering, DevOps, or AI platform engineering.
- Strong programming experience in Python.
- Hands-on experience with Databricks and Azure ML.
- Strong understanding of MLOps and LLMOps lifecycle and architecture.
- Experience with Kubernetes and OpenShift.
- Hands-on experience with GPU infrastructure and GPU-based ML/LLM workloads.
- Experience with MLflow for experiment tracking, model registry, and deployment.
- Experience with LangFuse and/or OpenTelemetry for LLM/AI observability.
- Knowledge of vector databases such as:
- Pinecone
- FAISS
- Chroma
- Milvus
- Experience with ML/AI frameworks including Hugging Face, PyTorch, and/or TensorFlow.
- Strong experience building CI/CD pipelines using Jenkins and/or Azure DevOps.
- Understanding of model governance, monitoring, observability, model drift, and performance management.
- Experience deploying ML/AI solutions into production environments.
Preferred Skills
- Experience with LLM, Generative AI, RAG, embeddings, and vector search.
- Knowledge of LLM inference and serving frameworks such as vLLM, KServe, or similar platforms.
- Experience with Azure cloud services and cloud-native AI architectures.
- Knowledge of Docker and containerized ML workloads.
- Experience with model optimization, quantization, and GPU resource optimization.
- Understanding of AI security, responsible AI, and enterprise model governance.
- Experience implementing automated LLM evaluation and quality monitoring.
- Familiarity with infrastructure-as-code tools such as Terraform or Ansible.
Key Competencies
- Strong problem-solving and troubleshooting skills.
- Ability to design scalable and reliable AI platforms.
- Strong understanding of production ML/AI deployment challenges.
- Excellent collaboration and communication skills.
- Ability to work effectively with Data Science, AI, Cloud, DevOps, and Engineering teams.
- Strong focus on automation, reliability, security, and operational excellence.