Were growing our AI department and are looking for a Senior MLOps Engineer to build the platform that takes our models and LLM systems reliably into production.
Role OverviewWe are looking for a Senior MLOps Engineer to design, build, and own the infrastructure and workflows behind our machine learning and LLM-powered systems. Your core work will be creating a reliable path from experimentation to production: training and fine-tuning pipelines, model registries, automated deployment, scalable inference, and monitoring for models running in cloud, on-prem, and air-gapped environments.
This is a senior, hands-on role. Youll define MLOps standards and platform architecture, make key decisions on reliability, scalability, and cost, and provide technical guidance to AI Developers and RAG Engineers on the team. Youll work closely with engineering, product, and client stakeholders to make sure AI features are reproducible, observable, secure, and ready to scale.
Key ResponsibilitiesMLOps Platform & Engineering (core focus)
- Design, deploy, and operate MLOps platform infrastructure, cloud services (AWS, Azure, GCP), and LLM inference pipelines (Ollama, vLLM).
- Build automated CI/CD pipelines, IaC, and monitoring/alerting systems to support RAG applications, AI agents, and production deployments.
- Manage Linux servers, networking, security endpoints, and troubleshoot production issues alongside AI engineering teams.
Technical Leadership
- Establish department-wide MLOps/DevOps standards, best practices, and reusable infrastructure templates.
- Partner with AI Developers and RAG Engineers to guide architecture, deployment strategies, tool selection, and production readiness.
- Translate feature requirements into reliable, secure, cost-effective infrastructure and maintain comprehensive system documentation.
Infrastructure & Operations
- Provision containerized workloads, Linux servers, and infrastructure using IaC (Terraform, Ansible) across cloud and on-prem environments.
- Manage CI/CD (GitHub Actions, Azure DevOps), observability tools (Prometheus, Grafana), secure networking, and GPU-enabled hardware.
- Troubleshoot platform incidents, perform root cause analysis, and maintain operational resilience.
Requirements- 5+ years of senior-level experience in DevOps/SRE/platform engineering with at least 1 year deploying ML models and LLM inference engines (Ollama, vLLM) in production.
- Proficiency with Linux, Docker, Kubernetes, virtualization (Proxmox, VMware), GPU infrastructure (CUDA/NVIDIA), and major cloud platforms (AWS, Azure, GCP).
- Hands-on expertise with Infrastructure as Code (Terraform, Ansible), CI/CD platforms (GitHub Actions, Azure DevOps), Bash, and Python scripting.
- Solid background in core networking (DNS, TLS, firewalls, VPNs), monitoring/logging, and security/authentication (OAuth2/OIDC, API gateways, Zero Trust/SOC 2).
- Familiarity with ML tooling (MLflow, Kubeflow), vector DBs, RAG/agent frameworks (MCP), workflow orchestration (Airflow/Kafka), and model optimization/quantization.
