ML Systems Engineer – End-to-End Inference & RL

Togetherai; San Francisco (CA); On-site; USD 200,000 - 280,000; Full time

Benefits offered by this job

Startup equity

Health insurance

Competitive benefits

Job summary

Togetherai is seeking a research engineer to enhance inference efficiency in production systems. This role focuses on translating advanced RL algorithms into practical applications that improve latency, throughput, and model quality.

Ideal candidates should have 3+ years in ML systems, proficiency in Python, and experience with large-scale model training. The company promotes a collaborative environment and expects candidates to engage in hands-on implementation and optimization.

The US base salary range is $200,000 - $280,000, plus equity and benefits.

Qualifications

• 3+ years of experience in ML systems or large-scale model training.
• Strong coding ability in Python.
• Demonstrated experience owning complex technical projects end-to-end.

Responsibilities

• Design and prototype algorithms for low-latency inference.
• Profile and optimize performance across GPU and memory layers.
• Run experiments to understand trade-offs between model quality and latency.

Skills

Large-scale inference systems

Reinforcement Learning (RL)

Python programming

Performance optimization

Education

Advanced degree in Computer Science or related field

Tools

SGLang

TensorRT

CUDA

Job description

Togetherai is seeking a research engineer to enhance inference efficiency in production systems. This role focuses on translating advanced RL algorithms into practical applications that improve latency, throughput, and model quality.

Ideal candidates should have 3+ years in ML systems, proficiency in Python, and experience with large-scale model training. The company promotes a collaborative environment and expects candidates to engage in hands-on implementation and optimization.

The US base salary range is $200,000 - $280,000, plus equity and benefits.