Research Engineer, Core ML

Responsibilities

• Advance inference efficiency end-to-end

  • Design and prototype algorithms, architectures, and scheduling strategies for low-latency, high-throughput inference.
  • Implement and maintain changes in high-performance inference engines (e.g., SGLang or vLLM-style systems, speculative decoding like ATLAS, quantization).
  • Profile and optimize performance across GPU, networking, and memory layers.

• Unify inference with RL / post-training

  • Design and operate RL and post-training pipelines (e.g., RLHF, RLAIF, GRPO, DPO-style methods, reward modeling).
  • Optimize RL workloads with inference-aware techniques like async rollouts and speculative decoding.
  • Train, evaluate, and iterate on frontier models.
  • Co-design algorithms and infrastructure to identify bottlenecks.
  • Run ablations and scale-up experiments.

• Own critical systems at production scale

  • Profile, debug, and optimize under real workloads.
  • Drive roadmap items requiring engine modifications.
  • Establish metrics, benchmarks, and experimentation frameworks.

• Provide technical leadership (Staff level)

  • Set technical direction for cross-team efforts.
  • Mentor engineers and researchers.

Requirements

Deep expertise in one or more areas with breadth to work across the stack:

• Bias toward implementation and shipping.
• Expertise in: large-scale inference systems (SGLang, vLLM), RL/post-training for LLMs (GRPO, RLHF), model architecture, distributed systems/HPC for ML.
• Strong Python coding, performance profiling/optimization.
• Research foundation with track record (papers, open-source, production).

Minimum qualifications

• 3+ years experience in ML systems, model training/inference, or equivalent.
• Advanced degree in Computer Science, EE, or related field, or equivalent.
• Experience owning complex technical projects end-to-end.

Compensation

US base salary range: $200,000 - $280,000 + equity + benefits.