Research Intern – Reinforcement Learning (RL) - Onsite at Level AI

, California, United States -

Full Time

Start Date

Immediate

Expiry Date

26 Jun, 26

Salary

0.0

Posted On

28 Mar, 26

Experience

0 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Reinforcement Learning, Agentic AI, Small Language Models, RL Environments, RL Agents, Reward Models, Offline Learning, Online Learning, Multi-Agent Systems, Simulation Frameworks, RLHF, LLM Fine-tuning, Model Alignment, Probability, Optimization

Industry

Software Development

Description

🚀 Build the next generation of Agentic AI with us Our platform combines conversation intelligence, multimodal understanding, and agentic AI systems to power both human agents and autonomous AI agents across the entire customer experience lifecycle. A core part of this vision is our investment in custom Small Language Models (SLMs)—purpose-built for CX workflows—paired with reinforcement learning systems that continuously improve decision-making in real-world environments. We’re looking for a Research Intern (Reinforcement Learning) to join us in shaping this future. What you’ll do Design and build reinforcement learning environments that model real-world customer interaction workflows. Design RL agents that learn from these environments using real-world interaction data, rewards, and feedback loops Define reward models and feedback loops using real-world signals (outcomes and human feedback) Enable learning from production data by structuring interaction traces into training-ready datasets for offline and online learning Experiment with multi-agent systems and simulation frameworks for complex coordination and decision-making Collaborate with engineering and product teams to deploy, evaluate, and iterate on learning systems in production at scale. What we’re looking for Currently pursuing (or recently completed) a degree in Computer Science, AI, Machine Learning, or related field Strong understanding of reinforcement learning fundamentals Familiarity with RL environments and training libraries such as Verl and Tinker Strong foundation in probability, math, and optimization Passion for building real-world AI systems Nice to have Experience with RLHF, LLM/SLM fine-tuning, or model alignment Exposure to agent-based systems or multi-agent RL Prior research, projects, or publications in RL or applied ML Experience working with large-scale or production datasets Why Level AI Work on production-grade Agentic AI systems used by leading enterprises Build alongside a team with deep expertise from Amazon, Google, and Meta Be part of a fast-growing Series C AI company. Direct exposure to 0→1 AI innovation in CX and decisioning systems \n \n

Responsibilities

The intern will design and build reinforcement learning environments modeling real-world customer interaction workflows and develop RL agents that learn from these environments using real-world data and feedback loops. Responsibilities also include defining reward models, structuring interaction traces for training, experimenting with multi-agent systems, and collaborating on production deployment.