Aswath Ram A Srinivasan
Employers on the program
- 2026Amazon Web Services3 talks
Upcoming appearances
Who’s booked ahead? →Event dates shown; only events starting today or later count. 1 upcoming event.
-
AWS re:Invent 2026 – · Las Vegas, United States
- Mitigating prompt injection with structured outputs in Amazon Bedrock code talk Program source ↗
- Route, cache, and batch: a multi-model decision framework on Bedrock chalk talk Program source ↗
- Build the right inference strategy on Amazon Bedrock breakout Program source ↗
No upcoming appearances are currently recorded.
The year around now
Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.
Appearances by year
- AWS re:Invent
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| Nov 30, 2026 | AWS re:Invent 2026 | AWS re:Invent | breakout | Build the right inference strategy on Amazon Bedrock as Amazon Web Services Generative AI workloads place very different demands on inference. Customer support chatbots and coding assistants may prioritize responsiveness, while…Show lessGenerative AI workloads place very different demands on inference. Customer support chatbots and coding assistants may prioritize responsiveness, while large-scale document processing can favor greater cost efficiency. | |
| Nov 30, 2026 | AWS re:Invent 2026 | AWS re:Invent | code talk | Mitigating prompt injection with structured outputs in Amazon Bedrock as Amazon Web Services Prompt injection works because LLM outputs are unconstrained. Structured outputs in Amazon Bedrock compiles a JSON Schema into a grammar and enforces it during…Show lessPrompt injection works because LLM outputs are unconstrained. Structured outputs in Amazon Bedrock compiles a JSON Schema into a grammar and enforces it during decoding so every token the model emits is a valid position in the schema. | |
| Nov 30, 2026 | AWS re:Invent 2026 | AWS re:Invent | chalk talk | Route, cache, and batch: a multi-model decision framework on Bedrock as Amazon Web Services Treating every request the same is what makes inference expensive at scale, and most of that cost is repeat work you already paid for. |
Frequent co-speakers
| Speaker | Shared events | Shared talks | Last together |
|---|---|---|---|
| Chintan Vyas | 1 | 1 | 2026 |
| Chris Greenwood | 1 | 1 | 2026 |
| Mac Stevens | 1 | 1 | 2026 |
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.