CareerPlan

Senior Staff AI Engineer

BangaloreFull-time2026-10-30 → 2026-11-18

Core

Designing and deploying large-scale Reinforcement Learning (RL) architectures and systems for next-generation enterprise AGI platforms, bridging research and production.

Role type

Senior Staff AI Engineer (Reinforcement Learning Architect)

Builds

RL-driven AI reasoning models, scalable training architectures, multi-agent and hierarchical RL frameworks

Domain

Enterprise AI / Reinforcement Learning

Deliverable

production ML models

Required skills

Reinforcement Learning (RL) algorithms, Multi-agent RL (MARL), LLM training and fine-tuning, Distributed training systems, Simulation frameworks, Test-time compute optimization, Policy optimization, Reward shaping, Cloud-native infrastructure

Preferred skills

RL with Verifiable Rewards (RLVR), GRPO-like approaches, On-policy methods (PPO, A3C), Off-policy methods (SAC, DDPG), Chain-of-thought reasoning

Technologies

OpenAI Gym, Isaac Gym, PettingZoo, MuJoCo

Responsibilities

Define end-to-end architecture for RL-based systems including training pipelines and model serving; Apply cutting-edge RL techniques to solve complex enterprise problems; Design distributed training systems and optimize for performance and cost; Provide technical leadership and mentorship to AI engineers and researchers; Partner with product and platform teams to integrate RL solutions; Define frameworks for benchmarking and continuous evaluation of deployed models; Ensure RL systems align with ethical AI practices and regulatory standards

Seniority

Senior Staff, hands-on IC with leadership