AI Research Engineer

Zenteiq Aitech; Bengaluru; On-site; INR 1,800,000 - 2,400,000; Full time

Job summary

Keka Inc. is seeking a founding post-training specialist to own end-to-end alignment and reasoning pipelines for base models. You will design post-training recipes spanning RLAIF, Constitutional AI, and dense supervision to unlock frontier reasoning directly on base weights.

You will architect automated data synthesis, critique loops, and rubric-driven refinement while building scalable alignment infrastructure on distributed RL systems.

Qualifications

• 3+ years hands-on RL / fine-tuning experience on LLMs.
• Deep theoretical and practical understanding of policy gradient methods and reward shaping.
• Experience with distributed training/rollout architectures (Ray, DeepSpeed, vLLM).

Responsibilities

• Base model post-training: design and scale full-spectrum post-training workflows on base foundation models.
• RLAIF & Constitutional AI: architect automated preference-data synthesis and refinement pipelines.
• Process Reward Modeling (PRMs): construct and train step-level PRMs to evaluate granular reasoning steps.
• Verifiable reward & environment design: implement deterministic verifiers and hybrid reward functions.
• Alignment infrastructure: optimize distributed RL training and rollout loops across accelerator clusters.

Skills

Reinforcement learning

Python programming

Distributed training

Policy gradient methods

Reward shaping

Tools

Ray

vLLM

DeepSpeed

JAX/PyTorch accelerators

Job description

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.
• 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.

Required Skills

Reinforcement learning - Strong programming skills in Python