Skip to content
VoltaiVoltaiPalo Alto, CA

Research Engineer - Post-Training

Post-trains frontier AI models using reinforcement learning to autonomously handle semiconductor design tasks like chip architecture optimization, RTL code generation, simulations, and verification. Collaborates with hardware experts to build RL environments, reward functions, and evaluation frameworks.

Salary not listed
On-siteML Engineering

About the role

Responsibilities

  • Post-train frontier models to autonomously perform complex tasks across the semiconductor design and verification pipeline.
  • Propose and optimize chip architectures.
  • Generate and refine RTL code.
  • Run simulations.
  • Identify verification gaps and iteratively improve designs.
  • Collaborate with hardware design, verification, and computer architecture experts to design reinforcement learning environments.
  • Develop structured reward functions, scaling strategies, and evaluation frameworks.

Requirements

  • Experience creating and scaling RL environments for LLMs or multimodal agents.
  • Building high-quality evaluation datasets and benchmarks for complex reasoning or design tasks.
  • Working closely with domain experts in hardware and verification to define evaluation metrics, constraints, and simulation conditions.
  • Designing reward functions and feedback pipelines that balance correctness, performance, and design efficiency.
  • Running large-scale RL fine-tuning or post-training experiments for frontier models.
  • Applying reinforcement learning or curriculum learning to structured reasoning or symbolic domains.

Skills

Reinforcement LearningLLMsMultimodal AgentsRl EnvironmentsEvaluation DatasetsBenchmarksRtlHardware DesignVerificationChip ArchitectureReward FunctionsRl Fine-TuningCurriculum LearningSemiconductor Design

Similar roles

ML Engineering jobs
OpenRouter

Applied AI Engineer

OpenRouterUnited States

Build and productionize internal agentic workflows and tooling on OpenRouter to automate support and go-to-market operations. Requires build-over-buy conviction, reliability focus, domain knowledge in support/GTM, backend systems expertise, security mindset, and quantitative evals.

Salary not listed
RemoteML Engineering
Beacon AI

Software Engineer, Artificial Intelligence/LLM

Beacon AISan Carlos, CA

Build and ship production LLM-powered features for aviation safety platform, including RAG, tool-calling, evals, guardrails, and monitoring for cost/latency/quality. Requires prior experience shipping LLM apps with strong RAG and production engineering skills.

135k – 260k/yr
Hybrid5+ YOEML Engineering
Beacon AI

Software Engineer, Cloud Infrastructure

Beacon AISan Carlos, CA

Build and operate scalable AWS cloud infrastructure, LLM platforms, RAG systems, and data pipelines for an AI aviation platform. Requires strong AWS and LLM production experience; hybrid in San Carlos, CA.

135k – 260k/yr
Hybrid5+ YOEML Engineering
Cloudflare

Software Engineer, AI Agents

CloudflareUnited States

Build and ship production AI agents on Cloudflare's edge platform using Workers, Durable Objects, and AI tools. Requires strong TypeScript/Rust experience, observability expertise, and hands-on LLM tooling for evals, safety, and multi-agent systems.

Salary not listed
On-siteML Engineering
Cerebras Systems

CoDesign & NextGen Performance Engineer

Cerebras SystemsSunnyvale, CA

Characterize, analyze, and optimize performance of state-of-the-art AI models on Cerebras' wafer-scale hardware. Build performance models, optimize kernels and compilers, debug runtime behavior, and develop visualization tools to influence next-gen AI architecture.

Salary not listed
On-site3+ YOEML Engineering