Jyostna Seelam
Senior Manager and Engineering Lead, Software Engineering at Capital One
Richmond, Virginia technical leader with 19+ years of experience, now a senior engineering manager at Capital One working on cloud modernization, DevOps, observability and platform engineering. She founded and chairs the Richmond ACM chapter, mentors through ADPList, and has published on trustworthy AI and on cutting LLM context and token costs.
Key arguments & positions
- Writes about the hidden cost of "context bloat" — that most LLM spend is wasted context rather than necessary reasoning.
- Argues trustworthy AI has to scale in startups and enterprises alike, and published a book chapter making that case.
- Advocates context-aware chatbot architecture on cloud platforms over bolt-on prompt tricks.
- Works from a cloud modernization, DevOps and observability background rather than a pure research one.
Accomplishments
- Senior Manager and engineering lead, Software Engineering at Capital One (2025); 19+ years in the field.
- Published the book chapter "Scaling Trustworthy AI in Startups and Enterprises" (Springer, 2026).
- Wrote "Supercharging Your Chatbot With Context-Aware AI on AWS" for DZone.
- Founder and chair of the Richmond ACM chapter, and a mentor on ADPList.
Papers & key writings
- "Scaling Trustworthy AI in Startups and Enterprises" (Springer book chapter, 2026)
- Google Scholar profile
- "Supercharging Your Chatbot With Context-Aware AI on AWS" (DZone)
Links
In the library
Nothing of theirs is filed in the hub yet. Browse the full library.
Recommended next
Hand-picked from the hub based on what Jyostna Seelam covers.
Generative AI for Beginners (Microsoft)
21 structured lessons on prompt engineering and building generative AI applications, with practical exercises in Python and TypeScript.
Why this: Also about prompt engineering
DeepLearning.AI
Free and low-cost AI courses, short courses, and newsletters from Andrew Ng's team.
Why this: Also about prompt engineering
Google Gemini Cheat Sheet
A three-page printable reference for Google Gemini: the PART prompt formula (Persona, Action, Reference, Tone), follow-up prompting, when to use Flash, Pro and Thinking models, saving your own context in settings, and worked sample prompts for Gemini inside Chrome, Gmail, Docs, Sheets, Slides and Drive. Includes a plain warning about Gemini being confidently wrong.
Why this: Also about prompt engineering
Thesis Statements by Mike Taylor
Column on prompt engineering, AI marketing experiments, and testing what actually works when you build with language models.
Why this: Also about prompt engineering