inDrive

Global ride-hailing platform with fare negotiation

Platform Engineer - Multiple Teams

Platform EngineeringUpdated on Nov 13

Full-timeLimassol, CyprusNo salary listed

About the Job

Requirements

At least 3 years of commercial backend engineering experience, including experience with high-load systems.
Strong Go skills, including production use of advanced language features.
Solid Python skills for data processing (batch, streaming, and asynchronous workloads) and service code.
Strong SQL skills in schema design, indexes, query optimization, and scaling approaches such as replication and partitioning; experience with Redis or similar key-value stores.
Experience with synchronous and asynchronous service communication using HTTP, gRPC, Kafka, or RabbitMQ, with a focus on reliability.
Experience with Docker and CI/CD pipelines, and working knowledge of Kubernetes.
Experience with core AWS or GCP 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 production concept drift; familiarity with scikit-learn, PyTorch, or TensorFlow.
Experience designing and operating observability systems, including metrics, logging, dashboards, tracing, and tools such as Prometheus, Grafana, or ELK.
Experience with Git workflows and code review; comfort with the Linux command line; and networking fundamentals including TCP/IP, DNS, VPCs, and load balancers.
Ability to clearly explain technical trade-offs to data scientists, product owners, and on-call engineers.

Responsibilities

Design, build, and operate backend services and internal tooling for the machine-learning platform using Go and Python, owning production delivery, monitoring, and on-call support.
Research and design new platform features, evaluate trade-offs, and document decisions.
Build and extend deployment tooling and software development kits that machine-learning teams use to ship models, including serving, autoscaling, and data capture.
Integrate machine-learning services with the wider backend using synchronous HTTP and gRPC and asynchronous Kafka and RabbitMQ communication, designed for reliability under high load.
Support the machine-learning delivery lifecycle with data scientists and machine-learning engineers, including CI/CD for models and pipelines, monitoring, and model-performance metrics.
Build end-to-end observability, including metrics, logs, dashboards, tracing, alerting, and runbooks.
Write infrastructure as code with Terraform and Terragrunt, and deliver it through reviewed pull requests.
Participate in code and design reviews, help raise engineering standards, mentor engineers, and review AI-generated changes to the same standard as human-written changes.

Desired Qualifications

Hands-on experience with MLOps tools such as Databricks (Unity Catalog and Asset Bundles), SageMaker, Kubeflow, MLflow, or Airflow.
GPU or large-language-model inference experience using tools such as vLLM, Triton, or Langfuse.
Experience using AI coding agents and fully reviewing their generated changes.
Experience in emerging markets or building in environments without an established playbook.
Experience with infrastructure-as-code tools.

inDrive runs many ML models across 48 countries, and the platform under them is growing fast. Teams ship to Databricks, SageMaker and self-managed GPU inference, and LLM workloads are moving into production.

We are hiring a Backend Engineer to build and run the services and tooling that ML teams depend on. You will write production-grade Go and Python, own your services from design to on-call, and learn the MLOps stack (Terraform, Kubernetes, Databricks, SageMaker) on the job. You will work with data scientists, ML engineers, and software and data engineers.

Design, build and run backend services and internal tooling for the ML platform, in Go and Python, and own them in production: delivery, monitoring, on-call.
Drive technical research and design for new platform features. Weigh trade-offs and write them down.
Build and extend the deployment tooling and SDKs ML teams use to ship models, including serving, autoscaling and data capture.
Integrate ML services with the wider backend: sync (HTTP, gRPC) and async (Kafka, RabbitMQ) communication, built for reliability under high load.
Support the full ML delivery cycle with data scientists and ML engineers: CI/CD for models and pipelines, monitoring, and model performance metrics.
Build observability end to end: metrics, logs, dashboards, tracing, alerting and runbooks.
Write infrastructure as code with Terraform and Terragrunt, and ship it through reviewed pull requests.
Take part in code and design reviews and help raise the engineering bar. Mentor engineers and hold AI-generated changes to the same review standard as human ones.

3+ years of commercial backend engineering, including high-load systems.
Strong Go: you know and have used its advanced features in production.
Solid Python for data processing (batch, streaming and async) and for service code.
Strong SQL: schema design, indexes, query optimisation, and scaling approaches such as replication and partitioning. Experience with Redis or similar key-value stores.
Experience with sync and async service communication (HTTP, gRPC, Kafka or RabbitMQ), with a focus on reliability.
Docker, CI/CD pipelines, and working Kubernetes knowledge. Experience with AWS/GCP core services (compute, storage, networking, IAM).
Understanding of the ML lifecycle: data preparation, model performance metrics, non-functional requirements, and concept drift in production. Familiarity with scikit-learn, PyTorch/TensorFlow.
Experience designing and running observability: metrics, logging, dashboards, tracing (Prometheus, Grafana, ELK or similar).
Git workflows and code review, comfortable Linux command line, and networking basics (TCP/IP, DNS, VPC, load balancers).
Ability to explain a trade-off clearly to a data scientist, a product owner and an on-call engineer.

Nice to have:

Hands-on experience with MLOps tooling: Databricks (Unity Catalog, Asset Bundles), SageMaker, Kubeflow, MLflow or Airflow.
GPU or LLM inference experience (vLLM, Triton, Langfuse).
Experience using AI coding agents with full review of generated changes.
Experience in emerging markets, or building where there is no playbook yet.
Experience with Infrastructure-as-Code (IaC) tools

About the Company

inDrive

Global ride-hailing platform with fare negotiation

inDrive operates a global mobility and urban services platform that connects passengers with independent drivers through a fare-negotiation system. Riders propose a trip price, and nearby drivers can accept, decline, or counteroffer, creating a peer-to-peer ride-hailing model. The service has expanded to intercity rides, delivery and cargo, groceries, advertising, and driver-focused fintech within its app. Unlike typical ride-hailing apps that use fixed fares, inDrive enables price negotiation and direct driver-rider interaction, and it pursues growth through a venture arm that funds ride-hailing-adjacent startups in emerging markets. This broader strategy aims to build a super-app for urban and gig-economy needs, with the goal of offering a wide range of mobility and urban services in 48 countries.

Company size: 10,001+
Company stage: Debt Financing
Total funding: $532M
Headquarters: Mountain View, CA
Founded: 2012

Recently Posted Jobs

Explore more opportunities at inDrive

See more jobs