ML Research Intern: Speculative Decoding for Fast Inference
Together Computer Inc
Together AI is seeking a research intern to advance speculative decoding, training and evaluating draft models at scale on dedicated GPU clusters in San Francisco. You will explore new drafters, verification schemes, and distillation recipes, testing ideas against real workloads and reporting results to the team. Join the Speculative Decoding group to push frontier models, work on efficient inference, and contribute to robust, reproducible evaluation across production-like traffic during a 12–14 #J-18808-Ljbffr Together Computer Inc
Vacancy posted 5 days ago
Similar jobs that could be interesting for youBased on the ML Research Intern: Speculative Decoding for Fast Inference in San Francisco, CA vacancy
- ...students to join a hands-on internship in San Francisco. The Inference Research team focuses on efficient, scalable serving systems for large... ...contribute to publications and blog posts while gaining exposure to cutting-edge ML research and system #J-18808-Ljbffr Together AIInternship
- ...and Who Why AI Researchers are the engine of... ...production, write internal reports that influence... ..., quantization, inference optimization (e.g., speculative decoding), hallucination mitigation... ...top venues — e.g., ML/AI conferences (... ...from zero in fast-paced startup or research...SuggestedContract workWork at officeImmediate startRemote workVisa sponsorshipRelocation packageFlexible hours
Ivo Inc.
San Francisco, CA1 day ago $250k - $325k
...and Who Why AI Researchers are the engine of... ...production, write internal reports that influence... ..., quantization, inference optimization (e.g., speculative decoding), hallucination mitigation... ...top venues — e.g., ML/AI conferences (... ...from zero in fast-paced startup or research...SuggestedContract workWork at officeImmediate startRemote workIvo Inc.
San Francisco, CA1 day ago- ...Pluralis Research works on Protocol Learning: training... ...Protocol Learning. Our inference pipeline generates the... ...keep this pipeline fast and reliable under these... ...shipped serving-engine internals or built a large-scale... ...deeply technical team of ML researchers. Pluralis is...SuggestedImmediate startRemote workVisa sponsorshipRelocation packageFlexible hours
Pluralis-Research
San Francisco, CA1 day ago - ...frontier AI labs build internally, made available to every... ...tasks like autonomous research, and the full-stack platform... ...Impact Build the inference systems that power... ...separating prefill from decode. Reduce trainer-to-inference... ...or a comparable ML framework. Ability to...SuggestedRemote workVisa sponsorshipRelocation packageFlexible hours
Prime Intellect, Inc.
San Francisco, CA5 days ago - ...Ambient.ai is on a fast-paced journey to... ...for inference, evaluation, and... ...engineering, production ML systems, LLM/LVM... ...partner closely with research scientists and product... ...compression, speculative decoding, distillation, pruning... ...building internal ML platforms or tools...Full timeWork at officeLocal areaFlexible hours3 days per week
- ...reason and act in real time. The Inference team builds the systems that make those models fast, reliable, and efficient at... ...AI. You don’t need to be an ML researcher—we’re looking for engineers... ...team on techniques such as speculative decoding and serving‑engine...Full timeFlexible hours
Candidate
San Francisco, CA1 day ago $230k - $390k
...reason and act in real time. The Inference team builds the systems that make those models fast, reliable, and efficient at... ...AI. You don’t need to be an ML researcher—we’re looking for engineers... ...team on techniques such as speculative decoding and serving-engine...Full timeFlexible hoursSierra
San Francisco, CA5 days ago$290k
...group of committed researchers, engineers,... ...Anthropic’s Inference organization serves... ...systems, ML infrastructure,... ...hardware (prefill and decode, batching,... ...on ambiguous, fast-moving efforts,... ...quantization, speculative decoding, or multi... ...correlate with the internal job level...Work at officeVisa sponsorshipFlexible hoursCandidate
San Francisco, CA2 days ago- DoorDash is seeking a Machine Learning Engineer intern to join our fast-growing engineering team. You will work on challenges in ML/AI and conduct research applicable to multiple DoorDash teams, with mentoring and external collaborations. The 12-week summer program will...InternshipSummer work
$203.5k - $299.3k
...hiring a Causal Machine Learning Engineer to help build the causal ML foundation behind how DoorDash grows New Verticals. This is not... ...you because you have…Deep practical experience with causal inference, econometrics, experimentation, or causal ML.Experience shipping...Hourly payWork at officeLocal areaRemote workFlexible hoursDoordash
San Francisco, CA6 days ago- ...simple to serve low-latency inference, fine-tune models, and... ...Seaborn,Luig i ), academic researchers, international olympiad medalists, and... ...inference research bets: speculative decoding, disaggregated prefill/... ...primitives for disaggregation, fast weight refresh for models...Work at office
Mixpeek
San Francisco, CA1 day ago $188k - $275k
...Of The Team The Inference team is... ...and workload-driven research rather than broad... ...bottlenecks in prefill, decode, KV cache usage, batching... ...as quantization, speculative decoding, caching... ...fun, and move fast! We’re in an exciting... ...alignment and internal equity when determining...Permanent employmentFull timeTemporary workCasual workWork at officeFlexible hoursCoreWeave
San Francisco, CA1 day ago$193.3k - $261.5k
...member of this team, you will lead research and development efforts in... ...interchangeable. Work towards a fast science-to-production paradigm.... ...transformer architecture, training/inference lifecycles, and optimization techniques- Knowledge of ML frameworks including JAX,...InternshipLocal areaFlexible hoursAmazonWebServices
San Francisco, CA4 days ago$215k - $260k
...That means owning the inference stack end to end: profiling... ...including prefill and decode disaggregation, request... ...across many kinds of ML models, with an emphasis... ...proofs of concept, run fast experiments to find... ...abilities, as well as internal equity and alignment with...Temporary workCrusoe
San Francisco, CA6 days ago- ...hiring a Causal Machine Learning Engineer to help build the causal ML foundation behind how DoorDash grows New Verticals. This is not... ...You Because You Have… Deep practical experience with causal inference, econometrics, experimentation, or causal ML. Experience shipping...Flexible hours
$200k - $260k
...Member of Technical Staff, Inference Engine You will build the core of our inference... ...workloads. Implement and tune speculative decoding, prefix caching, and structured-output... ...work. Open-source contributions to ML systems or runtimes. Cut p99 latency...ATBF Labs
San Francisco, CA1 day ago- ...Applied Scientist Intern The dates for this internship are January... ...Reuters Labs is seeking a ML/NLP scientist intern with a passion... ...our customers through applied research and development of new... ...Challenge (Y)our Thinking, Act Fast / Learn Fast, and Stronger Together...InternshipWork at officeLocal areaFlexible hours
Thomson Reuters
San Francisco, CA5 days ago - Together AI in San Francisco is seeking a research intern to accelerate inference systems for large foundation models. You will explore distributed inference, compiler-aware optimization, and cross-layer strategies across models, systems, and hardware. Join a collaborative...InternshipHourly pay
- ...We're building a research cohort of senior domain experts in ML inference and GPU kernel engineering — spanning inference serving systems, kernel optimization, and large-model deployment infrastructure — to help evaluate how frontier AI models reason about hard, real-...Temporary work
AfterQuery
San Francisco, CA9 days ago $215k - $285k
...boundary of efficient inference and carry the result... .... We care about research that moves a real metric... ...inference: speculative and parallel decoding, quantization, sparsity... ...Research background in ML, systems, or a quantitative... ...LLM/VLM inference internals. A history of...ATBF Labs
San Francisco, CA1 day ago$8.5k - $16k
...About the Team The DoorDash Research Fellowship is a 3-month program... ...work on the hardest applied ML and AI problems in local... ...GPU clusters for training and inference budgets for experimentation... ...research infrastructure - our internal RL stack, training and evaluation...InternshipSummer workWork at officeLocal areaRemote workRelocationRelocation packageDoorDash
San Francisco, CA1 day ago- ...frontier AI labs build internally, made available to... ...tasks like autonomous research, and the full-stack platform... ...LLM serving, LLM inference optimization and RL... ...as quantization and speculative decoding. Perf Suites: Develop... ...Building ML Systems at Scale: 3+...Work at officeRemote workVisa sponsorshipRelocation packageFlexible hoursShift work
Prime Intellect, Inc.
San Francisco, CA1 day ago $246.5k - $339k
...highly skilled team of Applied AI/ML Scientists specialize in... ...and recommendations to causal inference, lifetime-value modeling, information... ...quickly.Extract insights from internal and external data (e.g.... ...’ll love working at FaireMove fast: You'll own meaningful problems...Work experience placementWork at officeLocal areaRemote workMonday to FridayFlexible hours3 days per weekFaire
San Francisco, CA2 days ago- Together AI, the AI Native Cloud, invites a Research Intern to join the Model Shaping team in San Francisco or Amsterdam. You will explore advanced post-training methods, efficient training techniques, and robust evaluation of foundation models while collaborating with...Internship
- About Phonic Phonic is a product and research lab focused on powering the most realistic,... ...team includes top-tier AI researchers, international olympiad medalists, and former founders.... ...research scientists and engineers to move fast from prototype to production Build the...InternshipWork at office
$164.7k - $339.08k
...ensuring data insights inform downstream ML applications and broader product improvements... ...on large-scale data, preferably within a fast-paced tech environment.Exceptional... ...interpret and apply insights from various causal inference techniques.Proven ability to influence cross...Work at officeLocal areaRelocationRelocation packagePinterest
San Francisco, CA5 days ago$250k
...Transluce is a non‑profit research lab building tools for... ...as predictive concept decoders and user model... ...Scaling up the training and inference pipelines to support... ...desire to understand ML systems and how they work... ...open to sponsoring international visas. #J-18808-Ljbffr...Work at officeVisa sponsorshipTransluce
San Francisco, CA1 day ago- ...ML/AI Research Engineer — Agentic AI Lab (Founding Team) Location:... ...integrated with our vector DBs and internal knowledge graph Train... ..., and alignment Optimize inference latency and GPU resource utilization... ...Startup DNA: resourceful, fast-moving, and capable of...Full time
Fabrion
San Francisco, CA1 day ago $250k
...Description Transluce is a fast-moving research lab building the public... ...reliable systems (training and inference pipelines) For more... ...knowledge in some area of ML research, such as interpretability... ...We are open to sponsoring international visas. #J-18808-Ljbffr...Visa sponsorshipTransluce
San Francisco, CA1 day ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to ML Research Intern: Speculative Decoding for Fast Inference. Be the first to apply!
Related searches
- machine learning researcher San Francisco, CA
- intern - quantum machine learning for quantum computing San Francisco, CA
- machine learning research scientist San Francisco, CA
- machine learning San Francisco, CA
- data engineer machine learning San Francisco, CA
- machine learning part time San Francisco, CA
- internship machine learning San Francisco, CA
- machine learning intern San Francisco, CA
- artificial intelligence - machine learning intern San Francisco, CA
- machine learning remote San Francisco, CA