AI Research Engineer
Bengaluru, India · Full-time
- Posted 5d ago
- From ZenteiQ’s careers page
- Location
- Bengaluru, India
- Type
- Full-time
- Experience
- 3+ years
- Department
- Research and Development (R&D)
Opens the listing on zenteiqai.keka.com
Let the right jobs find you
In your inbox every Wednesday and SaturdayPersonalised suggestions from verified career pages, matched to your role, location, level and skills.
About the role
Role Overview
As a founding post-training specialist, you will own the end-to-end alignment and reasoning stack taking base pre-trained models through advanced alignment. You will design and execute novel post-training recipes spanning RLAIF, Constitutional AI, and dense process supervision (PRMs) to unlock frontier reasoning and domain alignment directly on raw base weights.
Key Responsibilities
- Base Model Post-Training: Design and scale full-spectrum post-training workflows on base foundation models using algorithms like GRPO, PPO, DPO, and iterative rejection sampling.
- RLAIF & Constitutional AI: Architect automated preference-data synthesis, iterative multi-turn critique loops, and rubric-driven constitutional refinement pipelines to eliminate human annotation bottlenecks.
- Process Reward Modeling (PRMs): Construct and train step-level PRMs to evaluate granular reasoning steps, intermediate chain-of-thought derivations, and dense domain verification tasks.
- Verifiable Reward & Environment Design: Implement deterministic verifiers, execution sandboxes for code and math, and hybrid reward functions combining outcome checks with dense step feedback.
- Alignment Infrastructure: Optimize distributed RL training and rollout loops across accelerator clusters, maximizing rollout throughput, memory management, and inference-engine integration.
Candidate Requirements
- 3+ Years Hands-On RL / Fine-Tuning Experience: Demonstrated track record executing post-training on LLM base models (not generic software engineering or high-level API wrapper development).
- Algorithmic Depth: Deep theoretical and practical command of modern policy gradient methods, credit assignment, value function estimation, and reward-shaping dynamics.
- Dense Reward & Alignment Mastery: Concrete experience designing reward models (ORMs/PRMs), preference optimization objectives, or constitutional self-critique mechanisms.
- High-Throughput RL Stack: Strong fluency with distributed training and rollout architectures (such as Ray, vLLM, DeepSpeed, or custom JAX/PyTorch accelerator pipelines).
- Startup Velocity & Ownership: Ability to independently formulate research hypotheses, diagnose reward hacking or mode collapse, and deploy robust training runs under fast production cycles.
What We Offer
- Direct Architecture Ownership: Full technical authority over the post-training, alignment, and reasoning methodology of foundation models.
- High-Density Compute: Dedicated accelerator clusters to validate novel RL formulations and train production models end-to-end.
Skills they ask for
Pick one to see other roles that ask for it.
About ZenteiQ
Frontier AI for the physical worldZenteiQ builds foundation models from scratch in India and products that deploy them in industry, including in fully offline environments.
See all 9 roles at ZenteiQMore roles at ZenteiQ
See all 9- Product OwnerBengaluruProduct ManagementBengaluru, India5d
- Backend EngineerBengaluruSoftware DevelopmentBengaluru, India5d
- ML Systems EngineerBengaluruSoftware DevelopmentBengaluru, India5d
- Program ManagerBengaluru · Senior · On-siteProject and Program Management · Senior · On-siteBengaluru, India5d
Let the right jobs find you
In your inbox every Wednesday and SaturdayPersonalised suggestions from verified career pages, matched to your role, location, level and skills.