inDrive — yo‘lovchilar, haydovchilar, kuryerlar va bizneslarni bog‘laydigan taksi chaqirish va logistika marketplace’ini boshqaruvchi global transport va yetkazib berish kompaniyasi. Uning xizmatlariga shahar ichidagi safarlar, shaharlararo qatnov, kuryerlik va yuk yetkazib berish, shuningdek inDrive.Money orqali iste’molchilar va haydovchilarga taqdim etiladigan moliyaviy xizmatlar kiradi. Kompaniya modeli foydalanuvchilarga tariflarni kelishib olish imkonini beradi, faoliyati esa bir nechta mamlakatlarda logistika, sayohat va marketplace bilan bog‘liq boshqa xizmatlarni qamrab oladi.
Senior Backend Software Engineer, AI Platform — inDrive
Build Go and Python services for inDrive’s machine learning platform, supporting models in production and MLOps tools. Help operate observable, high-load infrastructure serving systems across 48 countries.
Tavsif
- Build and operate Go and Python backend services and internal tools for the machine learning platform.
- Take production services through delivery, monitoring and on-call support.
- Research and design platform features, recording key technical trade-offs.
- Develop deployment tools and SDKs for model serving, autoscaling and data capture.
- Connect machine learning services to backend systems through synchronous and asynchronous communication.
- Work with data scientists and ML engineers on model and pipeline CI/CD, monitoring and performance metrics.
- Provide end-to-end observability through metrics, logs, dashboards, tracing, alerts and runbooks.
- Manage infrastructure as code with Terraform and Terragrunt using reviewed pull requests.
- Join code and design reviews, mentor engineers, and assess AI-generated changes to the same standards as other contributions.
- Work across data science, ML, software and data engineering teams.
Talablar
- At least five years of commercial backend engineering experience, including work on high-load systems.
- Strong production experience with Go, including its advanced features.
- Proficiency in Python for data processing and service development.
- Strong SQL skills, including schema design, indexing, query optimisation, replication and partitioning.
- Experience with Redis or a comparable key-value store.
- Experience with HTTP, gRPC, Kafka or RabbitMQ, with a focus on reliability.
- Experience with Docker and CI/CD pipelines, plus working knowledge of Kubernetes.
- Experience with core AWS or Google Cloud services for compute, storage, networking and identity and access management.
- Understanding of the machine learning lifecycle, including data preparation, model performance metrics, non-functional requirements and concept drift.
- Familiarity with scikit-learn, PyTorch or TensorFlow.
- Experience designing and operating observability systems with metrics, logging, dashboards, tracing, alerts and runbooks.
- Experience with Prometheus, Grafana, ELK or similar tools.
- Familiarity with Git workflows, code review, the Linux command line and networking fundamentals such as TCP/IP, DNS, VPCs and load balancers.
- Ability to explain technical trade-offs clearly to data scientists, product owners and on-call engineers.
- Helpful additional experience: MLOps tools such as Databricks, SageMaker, Kubeflow, MLflow or Airflow; GPU or LLM inference; AI coding agents; emerging markets; or infrastructure-as-code tools.
Imtiyozlar
- Work at global scale, with production models serving a worldwide fleet, meaningful GPU budgets and LLM workloads.
- Opportunity for backend engineers to grow into MLOps, with platform-side teaching available.
- Build professional skills through mentoring, career consulting and learning programmes.
- Join the Global Talent Exchange Program for international experience.
- Take part in company-wide challenges, awards, sports, employee-led social impact and volunteering.
- Access co-funded language courses and internal speaking clubs.
- Benefits may vary by location.