Senior ML Engineer: Real-Time Inference & Streaming (AWS)

TWG Global AI; New York (NY); On-site; USD 190,000 - 290,000; Full time

Job summary

TWG Global AI is seeking a Senior ML Engineer for AWS and Real-Time Inference to own the fast path: ingest live trading data and score it in near real time. This is a systems-heavy role focused on streaming, low-latency inference, and the retraining cadence that keeps models current with live markets.

You will develop streaming pipelines feeding model training and inference, connect the real-time detector service to a run-time model while managing latency under load, and coordinate feature

Qualifications

• Experience with streaming systems (Kafka, Kinesis, MSK) and modern data formats.
• Experience building low-latency, high-throughput inference services.
• Proficiency in Go and Python; production AWS experience.

Responsibilities

• Streaming pipelines and storage feeding model training and low-latency inference.
• Own online inference path; connect real-time detector to run-time model while maintaining latency under load.
• Manage model retraining cadence as data and labels accumulate, including drift-triggered retraining.
• Productionize new features/detectors on the fast path in partnership with data science.

Skills

Streaming systems

Low-latency inference

Go programming

Python programming

Production AWS experience

Tools

Kafka

Kinesis

MSK (Managed Streaming for Kafka)

FIX protocol

Job description

TWG Global AI is seeking a Senior ML Engineer for AWS and Real-Time Inference to own the fast path: ingest live trading data and score it in near real time. This is a systems-heavy role focused on streaming, low-latency inference, and the retraining cadence that keeps models current with live markets.

You will develop streaming pipelines feeding model training and inference, connect the real-time detector service to a run-time model while managing latency under load, and coordinate feature