L

Research Engineer - Inference

ladders • United States
Visa Sponsorship Relocation
Apply Now

Seeking a Research Engineer focused on advancing high-performance inference systems for reinforcement learning workflows and long-horizon agent workloads. The role involves improving throughput, concurrency, and efficiency across distributed ML infrastructure while reducing latency and accelerating end-to-end performance. Requires 5+ years in GPU inference systems optimization, strong Python and PyTorch proficiency, and experience profiling and debugging ML workloads.

Key Highlights
High-performance inference systems for reinforcement learning and long-horizon agents
GPU inference optimization with expertise in Python, PyTorch, and distributed ML infrastructure
$150,000–$350,000 annual salary with equity, visa sponsorship, and relocation assistance
Key Responsibilities
Extend inference integration for new model architectures used in RL training
Enhance rollout throughput for long-horizon agents by tuning concurrency
Optimize multi-node MoE inference with a focus on expert parallelism
Minimize trainer-to-inference weight-update overhead through sharding
Evaluate lower precision techniques and monitor numerical regressions
Collaborate with model researchers to improve inference efficiency
Technical Skills Required
Python PyTorch GPU Inference Optimization
Benefits & Perks
Cash compensation range of $150-350k, including equity incentives
Flexible work arrangements, with remote or in-person options
Visa sponsorship and relocation assistance for international candidates
Quarterly team off-sites, hackathons, and conferences
Nice to Have
Familiarity with vLLM or other inference engines
Knowledge of CUDA or Triton kernel development for low-precision inference

Job Description

For our client, we are seeking a Research Engineer - Inference to join the team of a leader in the Information Technology space.

This role will focus on advancing high-performance inference systems that support reinforcement learning workflows and long-horizon agent workloads. You will work at the intersection of model research and systems engineering, improving throughput, concurrency, and efficiency across distributed ML infrastructure. The position also involves close collaboration with researchers to reduce latency, improve numerical stability, and accelerate end-to-end training and inference performance.

Responsibilities

Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources
Keep exploring

Similar Jobs

Explore other opportunities that match your interests

OEC

Poland

Analytics Engineer

  • Python
  • ETL
  • Data Mining
  • Data Visualization
Full Remote

General Motors Llc

United States

Data Engineer

  • Python
  • ETL
  • Matlab
  • Embedded
Relocation

Career Resources & Guides

Latest guides related to this job: Visas, Work Permits & Legal Insights, Relocation Guides.

Browse all articles

Subscribe to our newsletter

New visa sponsorship, relocation and remote tech jobs, delivered to your inbox.