ApplySarthi Match jobs to your CV

Staff AI Engineer, Model Post-Training and Alignment

OKX

Make my CV for this job, freeView job and applyYour CV, rewritten for this role using only your real experience. Sign in with Google and upload your CV. Nothing to install.

Skills named in this job

Read from the description itself, not inferred.

This role on the market

10 open alignment roles across 4 companies are on ApplySarthi right now.

What alignment roles keep asking for: Machine learning (60%), LLMs (40%), Python (40%), Kubernetes (20%), NLP (20%), Supply chain (20%) — counted across their open postings here.

Remote AI Engineer jobs · LLMs jobs · Machine learning jobs

OKX has 342 open roles listed here.

Counted across 14 company job boards, updated as roles open and close.

Preparing for this interview

Interviews for alignment roles keep coming back to Machine learning, LLMs, Python, Kubernetes. Practise those questions before you sit with OKX.

Questions you are likely to be asked

  1. Why do you want to join OKX?
  2. What is your experience with Machine learning? Tell me one thing you learned the hard way.
  3. What would you check first if a model's accuracy dropped after going live?
  4. When would you not use machine learning for a problem?
  5. Walk me through a model you built, from the data to how it was used.

Prep Sarthi gives you a free mock interview: an AI interviewer asks you questions like these out loud, from your own CV and this job, and shows your score and your weakest answer.

Practise the Staff AI Engineer, Model Post-Training and Alignment at OKX interview free →

Who We Are

At OKX, we believe that the future will be reshaped by crypto, and ultimately contribute to every individual's freedom. OKX is a leading crypto exchange, and the developer of OKX Wallet, giving millions access to crypto trading and decentralized crypto applications (dApps). OKX is also a trusted brand by hundreds of large institutions seeking access to crypto markets. We are safe and reliable, backed by our Proof of Reserves. Across our multiple offices globally, we are united by our core principles: We Before Me, Do the Right Thing, and Get Things Done. These shared values drive our culture, shape our processes, and foster a friendly, rewarding, and diverse environment for every OK-er. OKX is part of OKG, a group that brings the value of Blockchain to users around the world, through our leading products OKX, OKX Wallet, OKLink and more.

About the Opportunity

We are seeking a highly skilled and hands-on Machine Learning Engineer specializing in large model post-training and alignment. This role focuses on designing, executing, and optimizing post-training pipelines to improve model performance, controllability, domain adaptation, and reasoning capabilities.

You will work across the full lifecycle of post-training—from data strategy and reward modeling to reinforcement learning–based optimization and production-grade inference deployment.

 

What You’ll Be Doing 

  • Lead and execute the full post-training pipeline for large language models (LLMs), including supervised fine-tuning, preference optimization, and reinforcement learning–based methods.
  • Design and implement advanced training paradigms such as DPO (Direct Preference Optimization) and GRPO (Generalized Reward Policy Optimization).
  • Develop domain-specific data recipes, curation strategies, and augmentation pipelines to optimize task performance.
  • Conduct post-training of specialized small models from scratch, including architecture selection, dataset construction, and optimization strategy.
  • Build and refine Reward Models to support alignment and downstream optimization.
  • Design and implement RLAIF (Reinforcement Learning from AI Feedback) closed-loop systems.
  • Optimize inference efficiency and deploy models using low-latency serving frameworks such as vLLM and SGLang.
  • Evaluate model performance using both automated benchmarks and human/AI feedback loops.
  • Collaborate with research and infrastructure teams to productionize training and deployment workflows.

 

What We Look For In You 

  • Bachelor's in Computer Science, AI, Machine Learning, or related fields with at least 8 years of industry experience.
  • Strong hands-on experience across the full post-training pipeline for large models.
  • Deep familiarity with preference learning and alignment techniques, including DPO, GRPO, and RL-based post-training methodologies.
  • Proven experience designing domain-specific data strategies and training methodologies.
  • Experience training and post-training specialized small models from scratch.
  • Solid understanding of reinforcement learning fundamentals and their application to model alignment.
  • Experience deploying models in low-latency production environments using frameworks such as vLLM, SGLang, or similar.

Perks & Benefits

Notice:
All official OKX vacancies are published on this website. While roles may appear on selected third-party platforms from time to time, information on other sites may be inaccurate or outdated. If in doubt, please apply directly through our official careers website.
Information collected and processed as part of the recruitment process of any job application you choose to submit is subject to OKX's Candidate Privacy Notice.

Match this job to your CV

ApplySarthi scores your CV against this role, shows the skills you are missing, and writes a tailored version for the application.

Check my match →

Similar open roles

Need answers during your interview? Try Live Sarthi.

Live Sarthi, an Interview Sarthi app, shows answer suggestions during the call.

Try Live Sarthi free →

A Windows app, from the same team as ApplySarthi.

Listed on greenhouse · posted 2026-03-19. ApplySarthi collects openings and links to application pages; the role is advertised by OKX, not by us.