EQ
Senior Research Engineer – Post-Training & Reinforcement Learning
Eternity Quests LLP · Delhi · onsite · Posted 39d ago
Not disclosed4–12 yrsfulltimeSourced from
About a minute. You'll make an account on the way through.
About this role
- Location: Delhi NCR
- Experiwnce - 4+ years
- Core Mandate: SFT, preference optimization, reasoning RL, reward modelling, verifier environments.
- Responsibilities:
- Drive model alignment and capability enhancement through Supervised Fine-Tuning (SFT).
- Implement and scale preference optimization techniques (e.g., RLHF, DPO) and advanced reasoning RL.
- Train robust reward models and engineer complex verifier environments to support iterative capability scaling.
- Requirements:
- 4+ years of applied experience in deep learning, specifically focusing on Reinforcement Learning, alignment methodologies, or post-training foundation models.
Sourced from foundit
Skills
Large Language Models (LLMs)RLHFPytorchreasoning modelsDPOModel AlignmentDeep Learningreward modellingLLM post-training