Groq delivers fast, efficient AI inference. Our LPU-based system powers GroqCloud™, giving businesses and developers the speed and scale they need. From our Bay Area roots to our growing global presence, 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.

Senior Machine Learning Engineer: Post Training & 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 TBD, determined by your skills, qualifications, experience and internal benchmarks.

Groq is an Equal Opportunity Employer. We are committed to creating an inclusive environment for all employees and applicants. All qualified applicants will receive consideration for employment without regard to race, color, religion, national origin, sex (including gender identity, sexual orientation, and pregnancy), age, disability, genetic information, protected veteran status, or any other characteristic protected by applicable law.

Groq complies with all applicable federal, state, and local laws governing nondiscrimination in employment. We do not tolerate discrimination or harassment based on any protected characteristic.

Groq is committed to working with and providing reasonable accommodations to qualified individuals with physical or mental disabilities. If you require a reasonable accommodation to complete an application or to participate in the hiring process, please contact us at talent@groq.com. This contact is for accommodation requests only, which will be considered on a case-by-case basis.

All offers of employment are contingent upon verification of the applicant’s identity and employment authorization in accordance with federal law.

Groq encourages people with criminal record histories to apply for employment, and values diverse experiences, including prior contact with the criminal legal system. To that end, Groq welcomes such applicants in accordance with the California Fair Chance Act, Los Angeles City Fair Chance Act Ordinance, Los Angeles County Fair Chance Act Ordinance, and San Francisco Fair Chance Act Ordinance. Philadelphia applicants can review information pertaining to Philadelphia’s Fair Criminal Record Screening Standards Ordinance here: https://www.phila.gov/documents/fair-chance-hiring-law-poster.

Ready to apply?

Powered by

First name *

Last name *

Email *

LinkedIn URL *

Phone number *

Location *

Resume *

Click to upload or drag and drop here

Website

Do you currently require, or will you require in the future, sponsorship for an employment visa (e.g., H-1B or similar) to legally work for our company in the country where this role is based? *

Worth Authorization

Voluntary Self-Identification

To comply with government reporting requirements, we invite candidates to participate in the self-identification survey below. Your completion of this form is entirely optional, and your decision will neither influence the hiring process nor any subsequent stages. Any information you choose to share will be kept confidential and stored in a secure file. As outlined in our Equal Employment Opportunity policy, we uphold a commitment to non-discrimination based on any protected group status specified in applicable laws.

Gender

Race

Race and ethnicity descriptions

Voluntary Self-Identification of Veteran Status

VEVRAA requires Government contractors to take affirmative action to employ and advance in employment protected veterans. To help us measure the effectiveness of our outreach and recruitment efforts of veterans, we are asking you to tell us if you are a veteran covered by VEVRAA. If you believe that you belong to any of the following categories of protected veterans, please indicate by making the appropriate selection.

Veteran status descriptions

Disabled veteran

A veteran who served on active duty in the U.S. military and is entitled to disability compensation (or who but for the receipt of military retired pay would be entitled to disability compensation) under laws administered by the Secretary of Veterans Affairs, or was discharged or released from active duty because of a service-connected disability

Recently separated veteran

A veteran separated during the three-year period beginning on the date of the veteran's discharge or release from active duty in the U.S military, ground, naval, or air service

Active duty wartime or campaign badge veteran

A veteran who served on active duty in the U.S. military during a war, or in a campaign or expedition for which a campaign badge was authorized under the laws administered by the Department of Defense

Armed Forces service medal veteran

A veteran who, while serving on active duty in the U.S. military ground, naval, or air service, participated in a United States military operation for which an Armed Forces service medal was awarded pursuant to Executive Order 12985 (61 Fed. Reg. 1209).

Veteran status

PUBLIC BURDEN STATEMENT: According to the Paperwork Reduction Act of 1995 no persons are required to respond to a collection of information unless such collection displays a valid OMB control number. This survey should take about 5 minutes to complete.

By applying you agree to Gem's terms and privacy policy.

Save your info to apply to other roles faster & help employers reach you.

Req ID: 438

Apply now

See more open positions at Groq

Privacy policy Cookie policy