29 days ago
Kazakhstan (city not specified)Senior
Responsibilities
- Design, build, deploy, monitor, and support high-load backend services and internal tooling for the ML platform using Go and Python.
- Build deployment tooling and SDKs for model serving, autoscaling, and data capture.
- Integrate ML services with backend systems through synchronous and asynchronous communication using HTTP, gRPC, Kafka, and RabbitMQ.
- Support model delivery pipelines, monitoring, and model performance metrics in collaboration with data scientists and ML engineers.
- Build end-to-end observability covering metrics, logs, dashboards, tracing, alerting, and runbooks.
- Create infrastructure as code with Terraform and Terragrunt and ship changes through reviewed pull requests.
- Conduct technical research, write designs, participate in code and design reviews, mentor engineers, and maintain review standards for AI-generated changes.
- Own services in production, including delivery, monitoring, and on-call support.
Requirements
- 5+ years of commercial backend engineering experience, including high-load systems.
- Strong production experience with Go and solid Python skills for data processing and service development.
- Strong SQL knowledge covering schema design, indexes, query optimization, replication, and partitioning, plus experience with Redis or similar key-value stores.
- Experience with reliable synchronous and asynchronous service communication using HTTP, gRPC, Kafka, or RabbitMQ.
- Working knowledge of Docker, Kubernetes, cloud compute, storage, networking, and IAM services on AWS or GCP.
- Understanding of the ML lifecycle, including data preparation, model performance metrics, non-functional requirements, and concept drift in production.
- Familiarity with scikit-learn, PyTorch, or TensorFlow.
- Experience designing and operating observability systems using metrics, logging, dashboards, and tracing tools such as Prometheus, Grafana, or ELK.
- Experience with Git workflows, code review, Linux command-line tools, and networking fundamentals including TCP/IP, DNS, VPCs, and load balancers.
- Preferred experience with Databricks, Unity Catalog, Asset Bundles, SageMaker, Kubeflow, MLflow, Airflow, GPU or LLM inference, vLLM, Triton, or Langfuse.
- Ability to clearly explain technical trade-offs to data scientists, product owners, and on-call engineers.
Benefits
- Access to mentoring, career consulting, learning programs, language courses, and internal speaking clubs.
- Global collaboration and international experience through the Global Talent Exchange Program.
- Company-wide challenges, awards, sports activities, employee-led social impact initiatives, and volunteering projects.
- Opportunity to work on globally scaled ML and LLM workloads with meaningful GPU and production constraints.
- Final benefits may vary depending on location.
Tech Stack
Apache AirflowApache KafkaAWSDatabricksDockerGitGoGoogle Cloud PlatformGrafanagRPCKubernetesLinuxMLflowPrometheusPythonPyTorchRabbitMQRedisscikit-learnSQLTensorFlowTerraform
Categories
About inDrive
inDrive builds a global mobility and urban services marketplace best known for ride-hailing, with additional offerings in intercity rides, delivery, and financial services. The privately held company is headquartered in Mountain View, California, and operates across 48 countries, monetizing through fees on transactions in its app. Its platform emphasizes driver–rider price negotiation and has amassed hundreds of millions of downloads.