Machine Learning Engineer: Post Training and Speculative Decoding
About Groq
Groq delivers fast, efficient AI inference. Our LPU-based system powers GroqCloud™, giving businesses and developers the speed and scale they need. Headquartered in Silicon Valley, we are on a mission to make high performance AI compute more accessible and affordable. When real-time AI is within reach, anything is possible. Build fast.
Machine Learning Engineer: Training and Speculative Decoding
Mission: We are seeking a highly skilled Machine Learning Engineer to join our advanced model development team. This role focuses on pre-training, continued training, and post-training of models, with a particular emphasis on draft model optimization for speculative decoding and quantization-aware training (QAT). The ideal candidate has deep experience with training methodologies, open-weight models, and performance-tuning for inference.
Responsibilities & outcomes:
- Lead pre-training and post-training efforts for draft models tailored to speculative decoding architectures.
- Conduct continued training and post-training of open-weight models for non-draft (standard) inference scenarios.
- Implement and optimize quantization-aware training pipelines to enable low-precision inference with minimal accuracy loss.
- Collaborate with model architecture, inference, and systems teams to evaluate model readiness across training and deployment stages.
- Develop tooling and evaluation metrics for training effectiveness, draft model fidelity, and speculative hit-rate optimization.
- Contribute to experimental designs for novel training regimes and speculative decoding strategies.
Ideal candidates have/are:
- 5+ years of experience in machine learning, with a strong focus on model training.
- Proven experience with transformer-based architectures (e.g., LLaMA, Mistral, Gemma).
- Deep understanding of speculative decoding and draft model usage.
- Hands-on experience with quantization-aware training, including PyTorch QAT workflows or similar frameworks.
- Familiarity with open-weight foundation models and continued/pre-training techniques.
- Proficient in Python and ML frameworks such as PyTorch, JAX, or TensorFlow.
Preferred Qualifications:
- Experience optimizing models for fast inference and sampling in production environments.
- Exposure to distributed training, low-level kernel optimizations, and inference-time system constraints.
- Publications or contributions to open-source ML projects.
Attributes of a Groqster:
- Humility - Egos are checked at the door
- Collaborative & Team Savvy - We make up the smartest person in the room, together
- Growth & Giver Mindset - Learn it all versus know it all, we share knowledge generously
- Curious & Innovative - Take a creative approach to projects, problems, and design
- Passion, Grit, & Boldness - no limit thinking, fueling informed risk taking
If this sounds like you, we’d love to hear from you!
Compensation: At Groq, a competitive base salary is part of our comprehensive compensation package, which includes equity and benefits. For this role, the base salary range is $175,900 to $307,800, determined by your skills, qualifications, experience and internal benchmarks.
Location: Some roles may require being located near or on our primary sites, as indicated in the job description.
At Groq: Our goal is to hire and promote an exceptional workforce as diverse as the global populations we serve. Groq is an equal opportunity employer committed to diversity, inclusion, and belonging in all aspects of our organization. We value and celebrate diversity in thought, beliefs, talent, expression, and backgrounds. We know that our individual differences make us better.
Groq is an Equal Opportunity Employer that is committed to inclusion and diversity. Qualified applicants will receive consideration for employment without regard to race, color, religion, national origin, gender, sexual orientation, gender identity, disability or protected veteran status. We also take affirmative action to offer employment opportunities to minorities, women, individuals with disabilities, and protected veterans.
Groq is committed to working with qualified individuals with physical or mental disabilities. Applicants who would like to contact us regarding the accessibility of our website or who need special assistance or a reasonable accommodation for any part of the application or hiring process may contact us at: talent@groq.com. This contact information is for accommodation requests only. Evaluation of requests for reasonable accommodations will be determined on a case-by-case basis.
