MLOps / LLMOps Engineer (GenAI Platform)

Role overview

Responsibilities

• check_circle Design, build, and maintain scalable AI/ML infrastructure for enterprise LLM applications.
• check_circle Deploy and optimize LLM inference workloads for high performance and low latency.
• check_circle Implement scalable model serving, monitoring, and observability solutions.
• check_circle Collaborate with AI researchers, data scientists, and software engineers to deliver production-ready GenAI solutions.
• check_circle Improve GPU utilization, model performance, and operational efficiency.
• check_circle Ensure AI governance, security, and Responsible AI compliance across deployments.

Basic qualifications

• 5–7 years of experience in <strong>MLOps, LLMOps, AI/ML Platform Engineering, or Machine Learning Engineering</strong>.
• Strong proficiency in <strong>Python</strong> and software engineering best practices.
• Hands-on experience with <strong>open-source LLMs</strong> such as <strong>Llama, Mistral, Gemma, or Qwen</strong>.
• Expertise in <strong>LLM inference and model hosting</strong> using technologies such as:
• vLLM
• SGLang
• Hugging Face TGI
• NVIDIA Triton Inference Server
• Ray Serve
• Azure Machine Learning
• Databricks Model Serving
• Experience with <strong>Kubernetes, Docker, Azure ML, Databricks, and MLflow</strong>.
• Strong understanding of:
• Retrieval-Augmented Generation (RAG)
• Vector Databases
• GPU Optimization
• Model Quantization
• KV Cache
• PagedAttention
• Continuous/Dynamic Batching
• Proven experience building, deploying, troubleshooting, scaling, and optimizing <strong>production-grade GenAI and LLM applications</strong>.
• Experience implementing AI observability, governance, and Responsible AI best practices.

Preferred qualifications

• Hands-on experience with <strong>LLM Fine-Tuning</strong> using:
• PEFT
• SFT
• CPT
• LoRA
• QLoRA
• Experience with:
• Azure AI Foundry
• Azure OpenAI
• Hugging Face
• DeepSpeed
• PEFT
• Knowledge of distributed training and multi-GPU environments.
• Experience with Agentic AI frameworks such as:
• LangGraph
• AutoGen
• CrewAI
• Familiarity with simulation platforms, digital twins, scientific computing, or modeling and simulation workflows.

Benefits

• check_circle Work on cutting-edge Generative AI and Large Language Model technologies.
• check_circle Build enterprise-scale AI platforms using modern cloud-native tools.
• check_circle Collaborate with highly skilled AI and ML engineering teams on innovative projects.