Digital Turbine, Inc.

Senior ML Systems Engineer - Productionization & Inference

Digital Turbine, Inc.
Apply
23 hours ago
Warsaw, PolandSenior

Responsibilities

  • Optimize feature extraction, transformation, joining, curation, and data-processing dependencies to reduce computation, data movement, and infrastructure costs.
  • Build reusable Python libraries, frameworks, tools, and workflows that move models from experimentation into production with minimal rework.
  • Optimize distributed training, GPU training, data caching, and resource allocation for ML workloads.
  • Build automated monitoring for feature drift and establish continuous-training triggers.
  • Evaluate execution strategies across native Python, Polars, Ray, Spark, ONNX, and CPU/GPU formats based on cost and performance.
  • Optimize models for inference by reducing duplicated computation and preparing efficient CPU/GPU formats for runtime ingestion.
  • Integrate productionized models with rAVE and other real-time inference components using strict payload contracts and integration patterns.
  • Automate model validation, packaging, versioning, testing, deployment, experiment tracking, and model-management workflows.
  • Profile workloads, identify CPU, memory, data-processing, and execution bottlenecks, and improve performance and reliability.
  • Provide production-ready tooling, documentation, and reusable components for Data Scientists.
  • Benchmark Polars and Ray on GKE against Spark and Databricks, and support IDE-native development with packaged, testable code.
  • Collaborate with Data Scientists, ML Engineers, and platform engineers to deliver production solutions.

Requirements

  • Strong Python engineering skills, including experience building reusable libraries and maintainable production software.
  • Experience productionizing machine-learning models or data-processing workloads beyond experimentation.
  • Understanding of experiment tracking, model versioning, validation, packaging, deployment, and the broader ML lifecycle.
  • Experience profiling and optimizing computationally intensive workloads and identifying CPU, memory, data-processing, and execution bottlenecks.
  • Experience designing automated testing and CI/CD workflows for data or ML systems.
  • Understanding of trade-offs among native Python execution, distributed processing, and infrastructure-heavy approaches.
  • Familiarity with Spark or PySpark and alternatives such as Polars or Ray, plus experience with large-scale data-processing pipelines.
  • Familiarity with Rust or experience working across language boundaries and establishing contracts with a Rust-based inference runtime.
  • Ability to collaborate with Data Scientists and software engineers and translate ML requirements into production-quality implementations.
  • Experience with Python data tools such as NumPy, pandas, and PyArrow; MLflow; Databricks; Spark/PySpark; Docker; GKE/Kubernetes; Airflow; and preferably GCP/GCS.
  • Additional experience with SQL, OLAP or OLTP systems, analytical and transactional data stores, ONNX, ONNX Runtime, GPU inference, PyTorch, Rust integration, Bigtable, Aerospike, feature stores, online feature serving, real-time data pipelines, advertising technology, bidding systems, or latency-sensitive environments is a plus.

Benefits

  • Competitive compensation, equity awards, and a comprehensive benefits package designed to support employee well-being.
  • Hybrid and flexible work environment.
  • Equal opportunity workplace committed to inclusion and diversity.

Tech Stack

Apache AirflowApache SparkDatabricksDockerGoogle CloudGoogle Cloud PlatformKubernetesMLflowNumPyPandasPythonPyTorchRustSQL

Categories

Data EngineeringML Engineering
Digital Turbine, Inc.

About Digital Turbine, Inc.

1,001-5,000 employees

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.

Contact me