Applied Research - RL & Agents

2 months ago

H1B sponsor

Base Salary

$150k - $300k/yr

Responsibilities

Design and implement novel reinforcement-learning and post-training methods, including RLHF, RLVR, and GRPO, for aligning large models with domain-specific tasks.
Design, prototype, and deploy AI agents, multi-agent systems, memory-augmented systems, evaluation harnesses, verifiers, and environments for real-world workflows.
Build frameworks, reference implementations, examples, and recipes for research platform offerings and open-source users.
Collaborate with research teams, infrastructure-heavy customers, and open-source contributors to design environments, evaluations, and verifiers.
Architect and maintain distributed training and inference pipelines for scalable and cost-efficient operation.
Develop production observability and monitoring using Prometheus, Grafana, and tracing.
Translate ambiguous application objectives into technical requirements that inform product and research priorities.

Strong machine-learning engineering background with experience in post-training, reinforcement learning, or large-scale model alignment.
Experience with agent frameworks and tooling such as DSPy, LangGraph, MCP, or Stagehand.
Familiarity with distributed training and inference frameworks such as vLLM, sglang, Accelerate, Ray, or Torch.
Track record of research contributions through publications, open-source contributions, or benchmarks in machine learning or reinforcement learning.
Strong technical writing abilities for documentation, blogs, or papers, along with research judgment and interest in reasoning and practical agentic AI systems.
Willingness to collaborate with external partners and the broader open-source community.
Preferred: experience with React, TypeScript, and Next.js; LLM evaluations or synthetic data generation; and Docker, Kubernetes, or Terraform at scale.

51-200 employees