
Lead ML Systems Engineer - Productionization & Inference Architecture
Digital Turbine, Inc.23 hours ago
Warsaw, PolandStaff+
Responsibilities
- Own the architecture and technical direction for ML productionization frameworks that move models from experimentation into production.
- Design reproducible workflows connecting Databricks-based development with production artifacts, feature pipelines, model validation, and deployment.
- Optimize feature extraction, transformation, joining, curation, data movement, and shared computation across analytical and production systems.
- Evaluate Python, Polars, Spark, Ray, ONNX, GPU execution, and other processing approaches for performance, scalability, operational complexity, and cost.
- Design model packaging, dependency management, testing, versioning, observability, and automated production delivery standards.
- Define payload contracts and integration patterns for productionized models running on rAVE and other real-time inference components.
- Investigate inference scalability strategies such as shared feature computation and reusable intermediate representations.
- Measure and improve productionization lead time, inference performance, resource utilization, infrastructure costs, and cost per prediction.
- Guide implementation decisions, mentor engineers, and align Data Science, ML Platform, feature infrastructure, and inference-runtime teams.
Requirements
- Strong software engineering background with deep Python expertise and experience designing reusable frameworks or platforms for production ML or data-processing workloads.
- Proven experience designing and operating production ML systems, including model lifecycle management, packaging, validation, deployment, and monitoring.
- Strong understanding of computational performance, profiling, memory management, parallelism, data-processing overhead, and resource utilization.
- Experience making architectural trade-offs across data-processing systems, data access patterns, execution environments, distributed processing, model-serving systems, and cloud infrastructure.
- Ability to balance model complexity, inference throughput, latency, infrastructure utilization, and total cost of ownership.
- Experience designing systems that integrate multiple models, shared features, or common computational components.
- Familiarity with Rust or experience working across language boundaries and establishing contracts with a Rust-based inference runtime.
- Experience with cloud infrastructure, automated delivery pipelines, production observability, and reliability engineering.
- Strong technical leadership, architecture ownership, cross-functional influence, and ability to turn ambiguous problems into an executable roadmap.
- Experience with Python data-processing tools including NumPy, pandas, and PyArrow; MLflow; Databricks; Spark or PySpark; production data-processing pipelines; model-serving interfaces; performance profiling; and observability.
- Experience with GCP, GCS, GKE, containerization, CI/CD, and Airflow is preferred.
- Rust, ONNX, ONNX Runtime, nvForest, PyTorch, GPU training or inference, neural-network serving, SQL, OLAP or OLTP systems, Bigtable, Aerospike, online feature stores, real-time feature pipelines, advertising technology, real-time bidding, and cost optimization for large-scale ML workloads are additional preferred experience.
Benefits
- Competitive compensation, equity awards, and a comprehensive benefits package.
- Hybrid and flexible work environment.
- Global work environment spanning North America, EMEA, APAC, and LATAM.
- Equal opportunity employer committed to inclusion and diversity.
Tech Stack
Apache AirflowApache SparkDatabricksDockerGoogle Cloud PlatformMLflowNumPyPandasPythonPyTorchRustSQL
Categories
Data EngineeringML Engineering
About Digital Turbine, Inc.
Digital Turbine builds a mobile growth and monetization platform that connects advertisers, app developers, carriers, and OEMs through on-device app discovery, ad delivery, and data-driven optimization. Its products include on-device placements (Ignite), a demand-side platform, offerwall, and content media services that drive user acquisition and ad revenue. The company is publicly traded on NASDAQ (APPS) and is headquartered in Austin, Texas.