Senior ML Operations Engineer
at Deepintent
Belgrade, Serbia, hybrid, senior, full time
posted 31 Aug 2026
- Airflow
- Vector databases
- Generative AI
- Argo Workflows
- MLflow
- Prometheus
- NVIDIA drivers
- LLM
- Grafana
- CUDA
- Docker
- RAG
- Jupyter
- Spark
- cuDNN
- Python
- Kubernetes
About the role
Posted: 2026-08-31
DeepIntent is the leading healthcare marketing platform, purpose-built to help marketers plan, activate, and optimize data-driven campaigns with speed and precision. Trusted by the world’s top healthcare brands and their agencies, DeepIntent uniquely unites media, identity, and real-world clinical data to power privacy-safe, omnichannel marketing across every screen. Backed by patented technology and proven outcomes, DeepIntent’s platform delivers measurable audience quality and script lift at scale. Learn more at www.deepintent.com.
What you would do
DeepIntent is seeking an MLOps Engineer to join our European Data Infrastructure team. The MLOps Engineer will partner with our Data Science and AI teams to build and scale a high-performance machine learning and AI platform spanning our on-prem data centers and GPU resources - built on Python, Spark, Kubernetes, Docker, and modern orchestration frameworks (Argo Workflows, Airflow).
- Partner with Data Science and AI Engineering teams to adopt MLOps best practices and migrate training/inference workloads onto the platform
- Implement and maintain model tracking, versioning and experiment management (MLflow) with observability into model performance and drift
- Build CI/CD pipelines purpose-built for ML/AI artifacts (model registries, container image pipelines, automated retraining triggers)
- Continuously improve platform reliability, cost-efficiency and maintainability of the underlying codebase
- Establish monitoring and observability for ML/AI systems (Prometheus, Grafana) covering GPU utilization, model latency, throughput and custom ML metrics
- Design and operate ML/AI deployment infrastructure, including GPU cluster architecture, model serving and tool selection across training and inference workloads
- Build and maintain infrastructure for LLM and generative AI workloads, including model fine-tuning pipelines, vector databases, RAG architectures and inference optimization
- Collaborate with business units and Product on ML/AI-driven feature development
- Manage individual project priorities, deadlines and deliverables in a timely manner
What they are looking for
Read from job-boards.greenhouse.io, last seen 4d ago.