Research Engineer - Post-Training

Volt AI
Palo Alto
Workplace: OnsiteFull timeFunction: Education & TrainingSkills: ["Reinforcement learning","Communication","Collaboration","Problem-solving"]

Post-train frontier models for semiconductor design and verification by building RL environments, evaluating design reasoning, and refining training pipelines. Collaborate with hardware and verification experts to create benchmarks, rewards, and evaluation frameworks that push models toward reliability and efficiency in silicon systems.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Volt AI
Volt AI
10 months ago

Research Engineer - Post-Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 15 hours agoStatus: Live

Job Summary

Post-train frontier models for semiconductor design and verification by building RL environments, evaluating design reasoning, and refining training pipelines. Collaborate with hardware and verification experts to create benchmarks, rewards, and evaluation frameworks that push models toward reliability and efficiency in silicon systems.
Location: Palo Alto
Workplace: Onsite
Employment Type: Full time
Job Function: Education & Training

Key Responsibilities

  • •Develop and scale reinforcement learning environments for semiconductor design workflows and verification tasks.
  • •Create and refine evaluation datasets/benchmarks to measure model reasoning and design capabilities.
  • •Collaborate with hardware and verification experts to define metrics, constraints, and simulation conditions.
  • •Design structured reward functions and feedback pipelines to optimize correctness, performance, and design efficiency.
  • •Execute large-scale RL fine-tuning or post-training experiments to advance frontier models.

Key Requirements

  • •Experience creating and scaling reinforcement learning environments for complex tasks (e.g., LLMs or multimodal agents).
  • •Ability to build high-quality evaluation datasets and benchmarks for reasoning or design tasks.
  • •Strong collaboration with domain experts in hardware and verification to define metrics and simulation conditions.
  • •Proven ability to design reward functions and feedback pipelines balancing correctness, performance, and design efficiency.
  • •Experience with large-scale RL fine-tuning or post-training experiments for frontier models.
Experience:SemiconductorHardwareVerificationRL environmentsReinforcement learning
Skills:Reinforcement learningCommunicationCollaborationProblem-solving
Tech Stack:RLLLMsMultimodalSimulationRTLBenchmarkingDatasets

Company Brief

Volt AI
Builds AI-driven software and solutions to automate business workflows, extract insights, and augment decision-making for enterprise customers across industries.
Industry: Enterprise Software
Website