Parna Mehta
AIOps Engineer, AWS Support Engineering at Amazon Web Services
Mumbai-based cloud and AI/ML engineer with close to 12 years in IT, working inside AWS Support Engineering where she triages and troubleshoots agentic AI, generative AI and retrieval-augmented systems. She holds six AWS certifications including the AI Practitioner credential, co-leads the BeSA volunteer tech community, and has spoken at Grace Hopper Celebration India.
Key arguments & positions
- From her conference talk: context windows are a budget, and "frugal" context engineering is how you keep production AI affordable.
- Works on the operational side of AI — triaging and troubleshooting agentic, generative and retrieval-augmented systems in support engineering.
- Connects cloud cost optimization to AI operations rather than treating them as separate disciplines.
- Active on mentorship and community building for women in tech.
Accomplishments
- AIOps Engineer in AWS Support Engineering; close to 12 years in IT.
- Holds six AWS certifications, including the AI Practitioner credential.
- Speaker at Grace Hopper Celebration India 2024.
- Recipient of an AWS global AWSome Award for customer obsession, and a top-three HerRising 2024 award in the Women Restarters category.
Papers & key writings
No published articles or papers found — her public record is conference talks and community work, so the themes above come from her role and her talk title.
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 Parna Mehta covers.
claude.dev — Anthropic Developers' Blog
Anthropic's developers share tips, playbooks and opinions on building with Claude and Claude Code, including agents, skills, context engineering and prompt caching.
Why this: Also about context engineering
The Complete Guide to Agent Harness
A long explainer on what an "agent harness" is — the loop, tools, memory, sandbox, permissions and budget caps wrapped around an AI model — its six core components, and why the wrapper now matters more than which model you pick. Opens with an agent that burned $400 in API calls overnight in a retry loop.
Why this: Also about context engineering