{bc}
linkedin

LLM Engineer (SFT / RLHF / Post-Training)

Achieve Group
Dubai, UAE
Fulltime
Mid-Senior
1 months ago
engineeringdesignproject managementmaintenancequality controltechnical
Free

Job Fit Check

Base Career helps you apply smarter for this job.

?%
Ready to Scan

Key skills for this role

engineeringdesignproject management
Smart Apply

Full Job Posting

Overview

We’re partnering with a leading global tech platform that builds next-generation AI systems used at massive scale.

This team focuses on

LLM post-training, reasoning, and alignment

— going far beyond prompt engineering.

If you have experience in fine-tuning, RLHF, or large-scale model training, this role offers meaningful opportunities to deepen your expertise.

What You’ll Be Working On

  • LLM post-training pipelines (SFT, DPO, RLHF)
  • Improving reasoning, alignment, and model reliability
  • Training and optimising models across 7B–100B+ scale
  • Building agent systems / tool-use / multi-step reasoning workflows
  • Working with large-scale GPU clusters and distributed training

What We’re Looking For

  • Hands-on experience with LLM fine-tuning (SFT, LoRA, etc.)
  • Exposure to RLHF / DPO / PPO / GRPO (any is an advantage)
  • Experience with LLaMA, Qwen, Mistral or similar models
  • Strong Python skills and deep learning frameworks (PyTorch, DeepSpeed, etc.)
  • Background in LLM, NLP, or applied ML systems

Why This Role

  • Remote work arrangement
  • Opportunity to work on cutting-edge LLM systems at global scale
  • Fast-moving, high-impact environment
  • Strong exposure to next-gen AI (reasoning, agents, alignment)

How To Apply

Submit your application by emailing a detailed copy of your updated

Resume in MS Word Format to Scarlett Zhang Jifan(EA Personnel Reg.

No.

R26159541, Achieve Career Consultant Pte Ltd EA Licence No. 05C3451)

by clicking the

“Apply Now”

or

email to Scarlett.zhang@achievegroup.asia

for a confidential discussion

• Current & Expected Salary

  • Reason(s) for leaving
  • Notice Period / Availability to commence work
  • YOUR SUCCESS IS OUR ACHIEVEMENT!
  • We regret only shortlisted candidate will be notified.
  • All applications will be treated with the strictest confidence.
  • By submitting any application or résumé to us, you will be deemed to have agreed and consented to us collecting, using, retaining and disclosing your personal information to prospective employers for their consideration.

Cessation Of Collection Of Full Nric Numbers

In compliance with the Personal Data Protection Act and commitment to protect candidates’ personal data, Achieve Group will cease to collect, process or use full NRIC numbers during our screening and job application process.

Kindly ensure your resumes provided to us does not contain your full NRIC number and full home address during your job application.

We regret that only shortlisted candidates will be notified.

Apply for this job in 1 click

Skip the repetitive application forms

Install the Base Career Chrome Extension and autofill job applications across major job boards with your profile.

Sarah M.James T.Maya R.

Trusted by over 500,000 job seekers on Base Career

Start Free Today