LLM Inference Engineer

Likely ghost job

πŸ•’ July 28

Where this job comes from

Posted on NEAR AI's careers page β†—NEAR AI's careers page, not through a job board

First seen by Remote Rocketship July 28

Still open on NEAR AI's site. Checked 4 hours ago.

Apply Now
Logo of NEAR AI

NEAR AI

11 - 50 employees

Founded 2017

πŸ€– Artificial Intelligence

πŸ”’ Cybersecurity

🏒 Enterprise

Artificial Intelligence β€’ Cybersecurity β€’ Enterprise

NEAR AI is a privacy-first AI infrastructure company that runs confidential inference and autonomous AI agents for enterprises, governments, and AI applications. Its NEAR AI Cloud and IronClaw agent framework execute models and workflows inside hardware-enforced Trusted Execution Environments (TEEs) with cryptographic isolation, zero operator access, and hardware-signed attestation for independent verification. NEAR AI offers a turnkey platform for deploying private models, automating repetitive operations, integrating with internal tools (Slack, email, Notion), and serving regulated or sovereign workloads via a marketplace of agents for finance, legal, ops, research and security.

πŸ“‹ Description

β€’ Architect and maintain production high-traffic LLM serving systems β€’ Optimize throughput, latency, and cost for leading open-source LLMs β€’ Push the boundaries of how large language models are served β€’ Contribute to decentralized and confidential machine learning infrastructure enabling user-owned AI β€’ Help build highly scalable and efficient infrastructure for open-source AI at global scale

🎯 Requirements

β€’ Strong hands-on experience in LLM inference, with expertise debugging and optimizing major inference engines such as SGLang, vLLM, or TensorRT β€’ Deep knowledge of state-of-the-art GPU architectures β€’ Ability to effectively exploit GPU architectures using PyTorch, Triton, CuTe, CUDA, etc. β€’ Proven track record in designing and maintaining end-to-end high-traffic LLM serving systems β€’ Strong problem-solving skills β€’ Ability to communicate technical ideas clearly β€’ Experience with Trusted Execution Environments (TEE) preferred as a nice-to-have β€’ Active contribution to open-source LLM inference engines preferred as a nice-to-have

πŸ–οΈ Benefits

β€’ Interview accommodations available upon request

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ July 28

Cerebras

501 - 1000

πŸ”§ Hardware

πŸ€– Artificial Intelligence

☁️ SaaS

Kernel Engineer developing high-performance software solutions at Cerebras optimizing deep learning operations. Collaborating within a world-class team for AI and HPC workloads on groundbreaking hardware.

πŸ•’ July 28

Wand AI

51 - 200

πŸ€– Artificial Intelligence

🏒 Enterprise

☁️ SaaS

Forward Deployed Engineer focused on designing and deploying AI solutions for enterprises. Involves hands-on technical work and strong customer engagement in a fast-paced startup environment.

πŸ•’ July 28

Surge AI

51 - 200

πŸ€– Artificial Intelligence

πŸ”Œ API

☁️ SaaS

Lead Adversarial Engineer managing red teaming against frontier models and ensuring awareness of risks. Collaborating across teams to validate findings and improve security protocols in AI systems.

πŸ•’ July 28

YA Group

501 - 1000

πŸ’Ό Consulting

πŸ—οΈ Construction

πŸ›‘οΈ Insurance

Senior Traffic Engineer at YA Group providing expert-level forensic consulting in traffic engineering. Evaluating roadway designs and ensuring compliance with engineering standards.

πŸ•’ July 28

TRM Labs

201 - 500

β‚Ώ Crypto

πŸ“‹ Compliance

🀝 B2B

Agent Engineer developing next-generation AI applications at TRM Labs. Focused on building robust AI infrastructures and agentic systems for investigative tasks.

Developed byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok