Senior ML/Ops Engineer (Python / Real-Time ML Systems)

About the Role

We are looking for a Senior ML/Ops Engineer to join a core algorithmic platform team building real-time ML inference systems at massive scale.

This is a highly technical, hands-on role focused on designing and operating production-grade ML systems, not research. You will work on systems that handle high throughput and strict latency requirements, with full ownership across backend, ML, and infrastructure layers.

Responsibilities

• Design, build, and maintain real-time ML inference services
• Develop and scale backend systems in Python
• Own end-to-end ML systems (architecture, services, pipelines, infrastructure)
• Integrate ML models into production services and business logic
• Optimize systems for low latency and high throughput
• Work with streaming systems and event-driven architectures
• Ensure system reliability, monitoring, and performance in production
• Collaborate closely with Data Scientists and engineering teams

Tech Stack

• Python (core language)
• Kafka / streaming systems
• Kubernetes, AWS / GCP
• FastAPI, Triton or similar inference frameworks
• Feature stores, model serving, A/B testing, monitoring tools
• High-performance data stores (Redis, Aerospike, etc.)

Requirements

• Strong backend engineering background in Python
• Hands-on experience with MLOps and production ML systems
• Experience building and owning end-to-end systems
• Experience with real-time / low-latency systems
• Experience working with high-scale environments (large traffic, high throughput systems)
• Strong system design skills (APIs, inference services, SLAs)
• Solid understanding of the ML lifecycle (training → deployment → monitoring)

Ideal Background

• Started as a Backend Engineer (Python) and transitioned into ML Engineering / MLOps
• Built production-grade ML services, not just pipelines
• Experience in high-scale domains (AdTech, Fintech, Gaming, streaming systems)

Important Notes

• This is a high-ownership role in a core team
• The domain is complex and niche — focus is on quality over quantity
• Experience with high-scale systems is highly preferred

Not a Fit If

• Pure DevOps / Infrastructure profile
• Only worked with ML pipelines (Airflow, ETL) without production ML
• No experience with real-time systems or latency constraints
• Mostly research or Data Science background without production systems

Hiring Process

• 2–3 interview stages

This role is ideal for engineers who combine strong backend engineering with ML systems experience and enjoy building real-time, high-scale production systems from end to end.