MLOps-Engineer für LLM-Performance (Kernel, Profiling, Serving)

Mercor
Softwareentwicklung
Remote
Freiberuflich

90 $ bis 120 $/Std.Richtwert laut Mercor

Veröffentlicht am 22. Oktober 2026 · Bewerbung bis 22. Dezember 2026

Auf Mercor bewerben

Ich leite Sie zur offiziellen Seite von Mercor weiter. Die Bewerbung ist kostenlos und auf Englisch.

Ich erhalte von der Plattform eine Provision, wenn ein von mir empfohlener Kandidat eingestellt wird. Für Sie ändert sich nichts.

Diese Stelle teilen

Der MLOps Engineer entwirft komplexe Aufgaben und Lösungen für Accelerator-Kernels, Leistungsprofiling und Inferenz-Serving, um fortschrittliche KI-Systeme zu trainieren. Die Rolle erfordert mindestens zwei Jahre praktische Berufserfahrung in ML-Systemen und den praktischen Umgang mit JAX oder PyTorch.

Beschreibung auf Englisch, wie von Mercor veröffentlicht.

Join a leading AI lab's cutting-edge GenAI team to be at the core of the AI revolution, where your expertise fuels the development of the most advanced Large Language Models.

1. Overview

Join a leading AI lab's cutting-edge GenAI team and help build foundational AI models from the ground up. We're seeking MLOps and ML systems engineers with hands-on experience in large language model infrastructure across any of four areas: accelerator kernel programming, performance profiling and trace analysis, debugging accelerated and distributed workloads, and high-throughput inference serving. Experience with JAX, XLA or TPUs is especially valuable. This role involves AI model training and evaluation work, including writing and assessing ML systems tasks and solutions to generate high-quality training data for frontier AI systems.

This is a fully remote role open to candidates worldwide. Depending on where you are based, your engagement will be arranged through Cincinnatus LLC or one of its trusted employer-of-record partners in your country, with the opportunity to be placed at a leading AI lab as part of their extended workforce. This is a 40-hour full-time engagement, with no conflicts/no other engagements.

2. Key Responsibilities

  • Design challenging tasks across kernels, profiling, debugging and inference serving, including adversarial problems that expose where frontier models fail on accelerator code (for example Pallas kernels on TPU), and write accurate, well-structured solutions to them.

  • Guide research and engineering teams to close knowledge gaps and improve AI model performance on ML systems, compilers and training infrastructure topics.

  • Evaluate ML systems tasks and solutions, and provide clear written technical feedback that stands up to expert review.

  • Develop guidelines and detailed rubrics covering kernel optimization, profiler output interpretation, distributed systems reasoning, and serving throughput and latency trade-offs.

  • Collaborate with other subject matter experts to keep training data consistent and accurate.

3. Core Qualifications

  • 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving, or accelerator performance engineering. This is a hands-on systems role rather than an applied modelling or data science one.

  • Practical experience in at least one of the following, with more than one a strong plus: writing or optimizing custom kernels (Pallas, Triton, CUDA, CUTLASS); performance profiling and trace analysis (JAX/XLA profiler, Kineto, torch.profiler, Nsight); debugging distributed or accelerator-bound workloads; serving large language models at scale (vLLM, SGLang, TensorRT-LLM, JetStream, KV cache, paged attention, continuous batching).

  • Working production experience with JAX and/or PyTorch. Framework-level depth is a strong plus: custom operators, sharding and distributed training (pjit/shard_map, FSDP, Megatron, MaxText), or compiler and graph-level work (XLA/StableHLO, torch.compile, MLIR).

  • Experience with modern accelerators such as TPU (v4 to v6e), H100, B200, Trainium or MI300, and the ability to reason about throughput, latency and memory trade-offs.

  • Demonstrable career progression.

  • Ability to engage reliably for at least 40 hours/week during weekdays.

  • Strong written communication skills and the ability to explain complex technical decisions clearly.

About Cincinnatus LLC: Cincinnatus LLC is an enterprise staffing company that partners with leading technology companies to source and engage highly skilled professionals for contingent and contract-based opportunities. Working directly or through local employer-of-record partners, Cincinnatus handles the employment or contracting relationship, payroll, benefits where applicable, and compliance in each country, while placing professionals directly within client teams to work on high-impact initiatives.

Equal Employment Opportunity: Cincinnatus is proud to be an Equal Employment Opportunity employer. We do not discriminate based upon race, religion, color, national origin, sex (including pregnancy, childbirth, reproductive health decisions, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, genetic information, political views or activity, or any other legally protected characteristic.

50 offene Stellen

Weltweit offen

Über Mercor

Mercor ist ein US-Marktplatz, der Remote-Experten für KI- und Beratungsprojekte einstellt, vom Recht bis zum Ingenieurwesen. Die Originalanzeige steht auf deren Website.

Diese Stelle auf Mercor ansehen

Ähnliche Stellen

Scientific / ML Engineer

Mercor
Datenanalyse
Remote
Nur Vereinigte Staaten
Teilzeit

The role involves guiding research teams, designing machine learning tasks, and writing reference solutions and rubrics for model evaluation. Candidates need four or more years of experience with PyTorch, JAX, or TensorFlow, plus strong Python skills.

Vor 13 Tagen veröffentlicht90 $ bis 140 $/Std.

Maintainer eines Open-Source-Projekts / Core Contributor, Softwareingenieur

Mercor
Softwareentwicklung
Remote
Freiberuflich

Die Rolle umfasst die Entwicklung realistischer technischer Aufgaben, das Verfassen von Referenzlösungen und die Bewertung von KI-generiertem Code für ein weit verbreitetes Open-Source-Projekt. Bewerber benötigen Erfahrung als Maintainer oder Core Contributor sowie ein Urteilsvermögen für Code-Reviews auf Senior-Niveau.

Vor 20 Tagen veröffentlicht150 $/Std.

DevOps / Infrastructure Engineer

Mercor
Softwareentwicklung
Remote
Nur Vereinigte Staaten
Teilzeit

The DevOps Infrastructure Engineer will guide research teams on cloud platforms, Kubernetes, and CI/CD topics, design realistic infrastructure tasks, and write technical feedback on AI training data. Candidates need 4+ years of production experience with Kubernetes, Docker, and infrastructure as code.

Vor 13 Tagen veröffentlicht80 $ bis 120 $/Std.

Embedded Systems / Kernel Engineer

Mercor
Softwareentwicklung
Remote
Nur Vereinigte Staaten
Teilzeit

The engineer guides research teams, designs low-level tasks covering memory management and device drivers, and writes technical feedback on solutions. Requires four or more years of professional embedded or kernel experience and strong production C or C++ skills.

Vor 13 Tagen veröffentlicht100 $ bis 150 $/Std.