1 day ago
Singapore, SingaporeStaff+
Responsibilities
- Design and implement unified reinforcement learning training pipelines combining model-based RL, offline RL, simulation, and online learning.
- Build latent world models and marketplace state representations for supply-demand interactions, location patterns, and behavioral signals.
- Develop multi-objective decision systems optimizing pricing, dispatching, and supply repositioning.
- Create policy evaluation and monitoring frameworks for safely deploying decision-making policies in production.
- Fine-tune open-source large language models for prediction, reasoning, and simulation in marketplace applications.
- Design language-model training strategies including supervised fine-tuning, preference-based alignment, and iterative improvement.
- Integrate RL and LLM systems into real-time production environments with data engineers and backend engineers.
- Lead a small technical team and guide research direction and production implementation.
Requirements
- PhD in Computer Science, Operations Research, Applied Mathematics, or a related field, with at least 10 years of experience.
- Proficiency in reinforcement learning fundamentals, including Markov Decision Processes, stochastic control, and reward design.
- Experience building production ML/RL systems with online learning or simulation-based optimization.
- Knowledge of world models and sequential modeling, including latent dynamic models, representation learning, RNNs, transformers, and state-space models.
- Hands-on experience fine-tuning large language models in production using supervised fine-tuning and at least one of RLHF, DPO, or GRPO.
- Experience with parameter-efficient methods such as LoRA, QLoRA, or PEFT and their accuracy, memory, and cost trade-offs.
- Ability to design generative-model evaluation frameworks covering factual accuracy and reasoning quality.
- Experience with distributed training frameworks such as DeepSpeed, FSDP, or Megatron-LM.
- Proficiency in Python and ML frameworks such as PyTorch or TensorFlow.
- Experience with scalable computing platforms such as Spark or Ray.
- Ability to translate ambiguous business problems into concrete modeling tasks, data requirements, and success criteria.
Benefits
- Term Life Insurance and comprehensive Medical Insurance.
- GrabFlex benefits package customization.
- Parental leave, Birthday leave, and Love-all-Serve-all volunteering leave.
- Confidential Grabber Assistance Programme.
- FlexWork arrangements with differentiated hours.
- Work from Grab’s One-North Singapore office.
Tech Stack
Categories
About Grab
Grab builds a Southeast Asia superapp for mobility, deliveries, and financial services, serving consumers, drivers, merchants, and enterprises. It monetizes via ride and delivery commissions, merchant services (such as ads and subscriptions), and payments and digital banking products. Founded in 2012 and headquartered in Singapore, Grab operates across multiple Southeast Asian markets and is publicly listed on NASDAQ.