- Location
- United States
- Workplace
- Remote
- Employment
- Full time
- Level
- Staff
- Posted
- 24 June
About this role
Mirendil
Mirendil is a tech-first company focused on solving core bottlenecks that unlock step-change acceleration across science and technology. Our first goal is to democratize frontier AI R&D across scientific disciplines. We believe accelerating scientific discovery is one of the most powerful ways to improve the future of humanity, and that AI will play a central role in making that possible.
We are building a frontier AI research company and training our own models end-to-end. Our work spans areas such as model training, reinforcement learning, reasoning systems, and infrastructure for large-scale experiments. Our team includes researchers and engineers from Anthropic, Google DeepMind, xAI, OpenAI, Microsoft, Apple, and MIT.
The Role
We are looking for an engineer to own the inference systems that power our models in production and research. You'll work across the full inference stack, from serving infrastructure down to hardware-level optimization. Some example areas you might work on (not limited to):
Design and build high-throughput, low-latency inference serving systems for frontier models, optimizing for both research iteration and production deployment
Optimize inference performance across GPU and accelerator hardware - maximizing FLOPs utilization, memory bandwidth, and compute efficiency for large-scale models
Enable and extend distributed inference frameworks (e.g. vLLM, SGLang, TensorRT-LLM) to support novel architectures, long-context workloads, and agentic inference patterns
Implement and validate inference-time optimizations: speculative decoding, quantization, KV cache management, and batching strategies
Build observability and reliability infrastructure so the team can measure latency, throughput, and cost across every serving configuration
Partner directly with teams to bring new model architectures and post-training techniques into production quickly
If you're excited about pushing the performance limits of frontier model inference, we'd love to hear from you.
We offer a base salary of $300,000 - $500,000 USD and a meaningful equity grant, depending on experience and background, along with competitive benefits.
As published by Mirendil. Applications are handled on their site.
Skills this posting mentions
About Mirendil
Mirendil is an AI research lab building self-accelerating systems that turn compute into scientific and engineering breakthroughs.
All 16 openings at MirendilOne click, then it is written
Apply to Mirendil with a resume written for this role.
Queue Member of Technical Staff, Inference and I read the posting, rewrite your resume against it, draft the cover letter, and score the fit. Then you press send, or press one button and I fill in Mirendil’s form for you.
01Drop your resume
A PDF or a LinkedIn URL. About a minute, once.
02I rank the openings
Every weekday morning, the live catalog scored against your history. Up to 20 worth your time, not two hundred links.
03Each one is written up
Resume rewritten for the posting, a cover letter, a fit score. Press send, or let me fill in the form.
- 25 sent a week, free
- No card
- Nothing sent until you say so
More roles at Mirendil
See all- 8 November
- 8 November
- 5 November
- 5 November
- 5 November
- 29 September
Similar roles elsewhere
See more- 20 November
Principal Software Engineer - Search Infra - Elasticsearch
ElasticUnited States
$160k - $304k/yrPrincipalEngineering - 20 November
Principal Software Engineer - Vector Search - Elasticsearch
ElasticUnited States
$160k - $304k/yrPrincipalEngineering - 20 November
Put this to work
Paste your career in once. Every application after that is written for you.
Drop a resume or a LinkedIn URL. I rank the live openings against it, rewrite the resume and write a cover letter for the best of them, and fill in the employer's form when you press the button. You read, you decide what goes out.
01Drop your resume
A PDF or a LinkedIn URL. About a minute, once.
02I rank the openings
Every weekday morning, the live catalog scored against your history. Up to 20 worth your time, not two hundred links.
03Each one is written up
Resume rewritten for the posting, a cover letter, a fit score. Press send, or let me fill in the form.
- New matches ranked and written before you are up.
- Every bullet stays inside what your history supports. Nothing invented.
- Queued, submitted, interviewing, offer: one screen, not a spreadsheet.
Free, no card. Up to 25 applications sent a week, and nothing is sent until you say so.
Listed from the job board Mirendil publishes. Refolk is not the employer and does not handle their hiring. Applications go to Mirendil directly.
Hiring at Mirendil? Post this role to the Refolk talent pool for $299, once. No commission, refunded if I find nobody. Post a role for $299