AI Systems Architect – Inference & RL at Scale

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 qualified engineer to join their Turbo team in San Francisco. The role focuses on advancing inference efficiency and operating Reinforcement Learning pipelines for ML systems. A candidate should have a strong background in systems and algorithms, with experience in Python and distributed systems.

With a commitment to innovation, Togetherai offers competitive compensation, equity, health benefits, and opportunities for growth in a dynamic work environment.

Qualifications

• 3+ years of experience working on ML systems or equivalent experience.
• Experience owning complex technical projects end‑to‑end.
• Demonstrated coding ability in Python.

Responsibilities

• Design and prototype algorithms for low-latency, high-throughput inference.
• Profile and optimize performance across multiple layers.
• Design and operate RL pipelines to enhance inference efficiency.

Skills

Large-scale inference systems

Reinforcement Learning (RL)

Model architecture design

Distributed systems

Python coding

Education

Advanced degree in Computer Science or related field

Tools

GPU performance profiling

TensorRT

SGLang

vLLM

Job description

Togetherai is seeking a qualified engineer to join their Turbo team in San Francisco. The role focuses on advancing inference efficiency and operating Reinforcement Learning pipelines for ML systems. A candidate should have a strong background in systems and algorithms, with experience in Python and distributed systems.

With a commitment to innovation, Togetherai offers competitive compensation, equity, health benefits, and opportunities for growth in a dynamic work environment.