Machine Learning Engineer (Real-Time Inference Systems)

Our client is a leading mobile marketing and audience platform empowering the global app ecosystem with advanced solutions in mobile marketing, audience building, and monetization.

With direct integrations into 500,000+ mobile apps worldwide, they process massive volumes of first-party data to deliver intelligent, real-time, and scalable advertising decisions. Their platform operates at extreme scale, serving billions of requests per day under strict latency and performance constraints.

About the Role

We are looking for a highly skilled, independent, and driven Machine Learning Engineer to own and lead the design and development of our next-generation real-time inference services.

This is a rare opportunity to take ownership of mission-critical systems on a massive scale, working at the intersection of machine learning, large-scale backend engineering, and business logic.

You will build robust, low-latency services that seamlessly combine predictive models with dynamic decision logic — while meeting extreme requirements for performance, reliability, and scalability.

Responsibilities

• Own and lead the design and development of low-latency inference services handling billions of requests per day
• Build and scale real-time decision-making engines, integrating ML models with business logic under strict SLAs
• Collaborate closely with Data Science teams to deploy models reliably into production
• Design and operate systems for model versioning, shadowing, and A/B testing in runtime
• Ensure high availability, scalability, and observability of production services
• Continuously optimize latency, throughput, and cost efficiency
• Work independently while collaborating with stakeholders across Algo, Infra, Product, Engineering, Business Analytics, and Business teams

Requirements

• B.Sc. or M.Sc. in Computer Science, Software Engineering, or a related technical field
• 5+ years of experience building high-performance backend or ML inference systems
• Strong expertise in Python
• Hands-on experience with low-latency APIs and real-time serving frameworks
  (FastAPI, Triton Inference Server, TorchServe, BentoML)
• Experience designing scalable service architectures
• Strong knowledge of async processing, message queues, and streaming systems
  (Kafka, Pub/Sub, SQS, RabbitMQ, Kinesis)
• Solid understanding of model deployment, online/offline feature parity, and real-time monitoring
• Experience with cloud platforms (AWS, GCP, or OCI)
• Strong hands-on experience with Kubernetes
• Experience with in-memory / NoSQL databases
  (Aerospike, Redis, Bigtable)
• Familiarity with observability stacks: Prometheus, Grafana, OpenTelemetry
• Strong sense of ownership and ability to drive solutions end-to-end
• Passion for performance, clean architecture, and impactful systems