Amazon Science

Research Services

Seattle, Washington 388,435 followers

The latest news and research from Amazon’s science community. #AmazonScience

About us

Amazon Science gives you insight into the company’s approach to customer-obsessed scientific innovation. Amazon fundamentally believes that scientific innovation is essential to being the most customer-centric company in the world. It’s the company’s ability to have an impact at scale that allows us to attract some of the brightest minds in artificial intelligence and related fields. Our scientists continue to publish, teach, and engage with the academic community, in addition to utilizing our working backwards method to enrich the way we live and work. Follow us on LinkedIn and visit our website to get a deep dive on innovation at Amazon, and explore the many ways you can engage with our scientific community. #AmazonScience

Website: https://www.amazon.science
External link for Amazon Science
Industry: Research Services
Company size: 10,001+ employees
Headquarters: Seattle, Washington
Founded: 2020
Specialties: Artificial Intelligence, Machine Learning, Computer Vision, Cloud, Economics, Sustainability, AI, ML, Conversational AI, Natural Language Processing, NLP, Robotics, Security, Privacy, Information, Knowledge Management, Operations, Scientific Research, Search, Amazon, and Alexa

Updates

Amazon Science reposted this
Andy Jassy Andy Jassy is an Influencer
2h
Report this post
Another exciting development in our chips business as Meta has decided to bet big on Graviton, our leading CPU chip—committing to tens of millions of Graviton cores. Agentic AI is becoming almost as big a CPU story as a GPU story. Complex multi-step orchestration, real-time reasoning, and code generation at scale is CPU-intensive work. And, our purpose-built Graviton5 instances deliver up to 33% lower latency between cores, which matters a lot for these kinds of workloads. Meta has been a longtime AWS customer and one of our biggest users of Bedrock... looking forward to what they build with Graviton5. https://lnkd.in/gQpphrPh

23 Comments

Like Comment Share
Amazon Science

388,435 followers
22h
Report this post
At ICLR, Amazon researchers are presenting papers spanning LLM reasoning, time series forecasting, reinforcement learning, and more. Explore their work:

1 Comment

Like Comment Share
Amazon Science

388,435 followers
1d
Report this post
Attending ICLR? Meet Amazon researchers across dozens of fields, catch live demos, and join us for expo talks. Find us at booth 106! #ICLR2026

1 Comment

Like Comment Share
Amazon Science

388,435 followers
2d
Report this post
Choosing the best AI model for antibody design has been nearly impossible without a diverse, ground-truth-validated benchmark. Amazon Web Services (AWS) and Johns Hopkins Whiting School of Engineering built one, spanning 50 seed antibodies, 4 structural formats, and 42 antigen targets.

AWS and Gray Lab at Johns Hopkins Whiting School of Engineering announce groundbreaking database for AI/ML antibody design Amazon Science on LinkedIn

Like Comment Share
Amazon Science

388,435 followers
3d
Report this post
At ICLR, Amazon researchers are presenting work on large language models, automated reasoning, and reinforcement learning. Join us at booth #106 to connect with our team, see live demos, and explore career opportunities. Check out our accepted publications: https://amzn.to/4tkG502 #ICLR2026
Like Comment Share
Amazon Science

388,435 followers
6d
Report this post
The Nitro Isolation Engine sets a new standard for cloud security as the first formally verified cloud hypervisor. Isabelle/HOL enabled verification of a quarter-million-line proof in 30 minutes. https://amzn.to/4vANcDd

Isabelle/HOL: The proof assistant behind the Nitro Isolation Engine

Like Comment Share
Amazon Science

388,435 followers
1w
Report this post
Training AI agents to click, type, and navigate real websites requires more than just a great model. Amazon's AGI Lab shares a practical recipe for scaling reinforcement learning into a reliable engine for computer-use agents. https://amzn.to/4vA60CD
1 Comment

Like Comment Share
Amazon Science

388,435 followers
1w
Report this post
Bringing a drug to market takes 10 to 15 years and costs over $2 billion on average. Using Amazon Nova Forge, Nimbus Therapeutics built its own customized frontier model, Novus, a scientific assistant trained in chemistry that will reason through molecular design. Through supervised and reinforcement fine tuning, one LLM now matches the performance of multiple specialized graph neural networks, unlocking the future potential of AI in drug discovery. https://amzn.to/4emDPki
Like Comment Share
Amazon Science

388,435 followers
1w
Report this post
Therapeutic antibody discovery remains slow and resource-intensive, with traditional methods providing limited control over epitope selection. We present a workflow for de novo nanobody design applied to a novel Desmoplastic Small Round Cell Tumor target encompassing four stages: (1) epitope identification guided by our hotspot recommendation agent using physical chemistry-based structure and sequence analysis tools with two curated databases (IEDB, PFAM), (2) de novo nanobody generation using three independent methods (RFantibody, IgGM, mBER) across multiple predicted antigen structures and nanobody frameworks, (3) multi-metric scoring including structural metrics from folding models, and in silico binding affinity from our sequencebased predictor, (4) high-throughput yeast surface display (YSD) screening followed by surface plasmon resonance (SPR) characterization of the specific binders. We generated 288,000 nanobody designs spanning eight target epitope regions and three variable domains of heavy chain-only antibody (VHH) frameworks. Multi-objective Pareto filtering with our candidate selection agent yielded 100,000 candidates for YSD screening with fluorescence-activated cell sorting (FACS). Of 116 enriched candidates advanced to SPR characterization, 46/116 (39.7%) produced reliable kinetic fits with Rmax ≥ 30 RU, yielding KD values from 0.66 nM to 305 nM (median 31.7 nM). These results show that an agent-guided computational workflow can design nanomolar to sub-nanomolar nanobody binders against a novel target without experimental structure or prior antibody information.

1 Comment

Like Comment Share
Amazon Science

388,435 followers
2w
Report this post
Amazon built RuleForge to tackle the challenge of 48,000 new vulnerabilities published in 2025. The agentic AI system generates production-ready detection rules 336% faster than manual methods: https://amzn.to/4dzAnCJ
3 Comments

Like Comment Share

Amazon Science

Research Services

Seattle, Washington 388,435 followers

The latest news and research from Amazon’s science community. #AmazonScience

About us

Updates

Isabelle/HOL: The proof assistant behind the Nitro Isolation Engine

Join now to see what you are missing

Affiliated pages

Amazon

Amazon Web Services (AWS)

Whole Foods Market

Twitch

Prime Video & Amazon MGM Studios

Amazon Ads

Amazon Lab126

Amazon Business

Amazon Fulfillment Technologies & Robotics

Souq.com

Goodreads

Audible

Sell on Amazon

IMDb.com

Transportation, Shipping, & Logistics at Amazon

Amazon Careers

Amazon Music

Amazon Leo

Ring

Amazon Pay

Shopbop

Amazon Alexa Developers

Amazon Development Center Poland

Amazon Associates

AbeBooks, an Amazon company

Amazon Fashion & Sports

Alexa.com

Amazon Ads Partners

A9.com

Amazon Kindle

Amazon Smart Vehicles

Amazon Pharmacy

Fulfillment by Amazon

Just Walk Out technology

Annapurna Labs

Amazon Developer

Curse

Woot, Inc.

Amazon Launchpad

Quidsi Inc., a subsidiary of Amazon

CreateSpace

LOVEFiLM

Comixology, an Amazon company

Buy with Prime

AWS Thinkbox

Brilliance Publishing

Amazon | Liquavista

Perceive

Amazon Autos

Sustainability & Community Action at Amazon

Amazon Help

Amazon News

Amazon in Action

Similar pages

Google

Microsoft

Apple

Deloitte

Netflix

Meta

Flipkart

Amazon Web Services (AWS)

IBM

Accenture