Python backend engineer

We are looking for a strong Python Backend Engineer to lead the development of next-generation real-time inference services in a large-scale mobile data platform.

The system processes billions of requests daily and requires extremely low latency, high throughput, and strong reliability. This role sits at the intersection of backend engineering, distributed systems, and ML model serving.

⚠️ Important: This role is focused on building inference infrastructure and real-time decision services, not on model training or algorithm research.

We are looking for an engineer who can design and scale high-performance distributed backend systems that run ML models in production and apply business logic on top of model outputs.

Responsibilities

• Design and develop low-latency real-time inference services
• Build scalable decision engines combining ML predictions with dynamic business logic
• Integrate services with feature stores and high-performance data layers
• Implement model versioning, shadow deployments, and runtime A/B testing
• Ensure high availability, observability, and performance of production systems
• Optimize latency, throughput, and infrastructure efficiency
• Collaborate with Data Science, Infrastructure, Product, and Engineering teams
• Propose and drive architecture improvements for distributed systems

Requirements

• 5+ years of experience as a Python Backend Engineer / Distributed Systems Engineer
• Strong experience building real-time or high-load backend systems
• Experience with low-latency APIs and async architectures
• Experience with ML model serving frameworks (FastAPI / BentoML / Triton / TorchServe or similar)
• Strong understanding of distributed systems architecture and message queues (Kafka / PubSub)
• Experience with cloud environments (AWS / GCP / OCI) and Kubernetes
• Experience with in-memory or NoSQL databases (Redis, Aerospike, Bigtable, etc.)
• Understanding of MLOps concepts and model deployment lifecycle
• Strong ownership mindset and ability to work independently
• Fluent English and strong communication skills

Nice to Have

• Experience building custom inference platforms
• Experience working with feature stores
• DevOps background
• Experience in high-scale product environments (AdTech / data platforms / real-time systems)
• Strong focus on performance optimization and system design

Hiring Process

• 2 stages: technical + interpersonal