Job Description:

About Us

Sea Group is establishing a brand-new, strategic AI department. This department is dedicated to exploring the transformative potential of generative AI in revolutionizing human connection, self-expression and communication diversity, and social interaction. We are building the next generation of AI-native applications and a comprehensive Model-as-a-Service (MaaS) product support system. Based on massive multi-country data, we are building a leading multilingual AI ecosystem from the ground up. We look forward to more outstanding talents joining us to build leading Southeast Asian multilingual models and explore innovative AI-native applications.

The AI application team focuses on the intersection of social connectivity and artificial intelligence. Our mission is to leverage LLMs to create digital personas that can act as personal assistants and social bridges. This team operates with a startup's agility backed by our Group's robust resources, aiming to define how humans interact in the AI era.

About the Job

Alignment & Tuning: Lead SFT and RLHF to enhance instruction following, reasoning, and persona consistency.
Synthetic Data RL: Build automated data pipelines using Self-Instruct, Evol-Instruct, and synthetic data reinforcement to scale model capabilities.
Safety & Alignment: Conduct Red Teaming and mitigate hallucinations, bias, and value misalignment.
Bad Case Analysis: Perform root-cause analysis on model errors to drive iterative optimization of prompts and fine-tuning strategies.

Requirements:

Master's/PhD in Computer Science or related fields Bachelor can be considered with a strong industrial experience.
Minimum 3 years of experience in LLM post-training.
Proven expertise in RLHF and LLM-as-a-Judge evaluation frameworks.
Strong coding skills in Python/Linux familiar with DeepSpeed/Megatron frameworks.
[Plus] Background in AI social/companion products or large-scale NLP evaluation.

[AI] LLM Algorithm Engineer (Post Training)