Member of Technical Staff, Inference & RL Systems

Magic; San Francisco (CA); On-site; USD 225,000 - 550,000; Full time

Benefits offered by this job

Equity compensation

401(k) with salary matching

Generous health, dental, and vision insurance

Unlimited paid time off

Visa sponsorship and relocation stipend

Job summary

Dormont Manufacturing Co is looking for a Software Engineer on the Inference & RL Systems team in San Francisco. The role involves designing distributed systems, optimizing performance, and ensuring high reliability for RL and post-training workflows.

The ideal candidate will possess strong software engineering fundamentals and experience with large-scale systems. Compensation includes a competitive salary range from $225K to $550K, along with equity, health benefits, and unlimited paid time off.

Qualifications

• Experience operating large-scale inference or training systems.
• Strong fundamentals in software engineering and distributed systems.
• Ability to reason about latency, throughput, and cost trade-offs.

Responsibilities

• Design and scale high-performance inference serving systems.
• Optimize KV-cache management and scheduling.
• Build and maintain distributed RL and post-training infrastructure.

Skills

Software engineering fundamentals

Distributed systems

GPU execution constraints

Performance debugging

System-level trade-offs

Job description

About the role

As a Software Engineer on the Inference & RL Systems team, you will design and operate the distributed systems that serve our models in production and power large-scale post-training workflows.

This role sits at the boundary between model execution and distributed infrastructure. You will work on systems that determine inference latency, throughput, stability, and the reliability of RL and post-training training loops.

Magic’s long-context models introduce demanding execution constraints: KV-cache scaling, memory pressure under long sequences, batching trade-offs, long-horizon trajectory rollouts, and sustained throughput under real-world workloads. You will own the infrastructure that makes both production inference and large-scale RL iteration fast and reliable.

What you’ll work on

• Design and scale high-performance inference serving systems
• Optimize KV-cache management, batching strategies, and scheduling
• Improve throughput and latency for long-context workloads
• Build and maintain distributed RL and post-training infrastructure
• Improve reliability of rollout, evaluation, and reward pipelines
• Automate fault detection and recovery for serving and RL systems
• Profile and eliminate performance bottlenecks across GPU, networking, and storage layers
• Collaborate with Kernels and Research to align execution systems with model architecture

What we’re looking for

• Strong software engineering and distributed systems fundamentals
• Experience building or operating large-scale inference or training systems
• Deep understanding of GPU execution constraints and memory trade-offs
• Experience debugging performance issues in production ML systems
• Ability to reason about system-level trade-offs between latency, throughput, and cost
• Track record of owning critical production infrastructure

Compensation, benefits, and perks (US)

• Annual salary range: $225K - $550K
• Equity is a significant part of total compensation, in addition to salary
• 401(k) plan with 6% salary matching
• Generous health, dental and vision insurance for you and your dependents
• Unlimited paid time off
• Visa sponsorship and relocation stipend to bring you to SF, if possible
• A small, fast-paced, highly focused team

Magic strives to be the place where high-potential individuals can do their best work. We value quick learning and grit just as much as skill and experience.