Enterprise AI in Production
A members-only meet-up by The Fifth Elephant
19 June 2026 | 1:45 PM – 6:00 PM | InMobi, Bengaluru
This meet-up is for engineers and architects who are past the prototype stage — dealing with inference costs, agent failures, security gaps, and the gap between what the benchmark said and what production revealed.
Confirmed speakers include practitioners from IDfy and Sahaj Software, with more being added.
Agenda highlights
📌 ₹11 lakh/month: how we took the GPU out of face match — moving face matching from GPU to quantized CPU inference via OpenVINO: the calibration, the failures, and the production canary. Vivek Kalyanarangan, Sr. Technical Architect, IDfy
📌 When the agent workflow survives production but the MCP server splits an RCE — what an audit of 50+ production MCP servers found, and how to stop vulnerable servers from reaching your agent workflow. Akash Sathish, Solution Consultant, Sahaj Software
📌 Live demos and lightning talks — submissions open until 15 June. Submit here.
Who should attend
✅ AI/ML and platform engineers operating production systems
✅ Backend and infrastructure engineers building AI workflows
✅ Engineering leads running AI initiatives at scale
✅ DevOps, SRE, and AppSec practitioners working with AI systems
Meet the editor
This meet-up is curated by Ramakrishna Reddy Yekulla (Ramky), who leads technical strategy and AI operationalization at Red Hat’s Data + AI group. A long-time open-source contributor across Fedora, Django, GNOME, and GlusterFS, Ramky’s focus spans AI infrastructure, systems architecture, and large-scale operational engineering.
How to attend
This meet-up is open to:
🎟️ Fifth Elephant community members — https://hasgeek.com/fifthelephant#memberships
🎟️ Ticket holders for The Fifth Elephant annual conference - https://hasgeek.com/fifthelephant/enterprise-ai-in-production-meetup#tickets
📞 Need more info?
☎️ Call: (91) 7676332020
📧 Email: info@hasgeek.com
Featured submissions
See all-
Akash Sathish
When the agent workflow survives production but the MCP server splits an RCE
Every enterprise AI workflow that matters in 2026 routes through MCP servers starting from the tools that give your AI agents access to files, databases, APIs, till shell commands. But the security posture of these servers is systematically poor: 43% have command injection vulnerabilities, 36% have SSRF exposure, and the real CVEs (CVE-2025-6514, CVSS 9.6) are execSync(args.cmd). These are bugs t… more31 May 2026
-
VK
Vivek Kalyanarangan
₹11 Lakh/Month: How We Took the GPU Out of Face Match
Face matching is one of the highest-volume workloads in identity verification. At IDfy, a single GPU pod handling 1 RPS cost us ₹3,500/day. After moving the model to BF16 inference on Intel CPUs via OpenVINO, the same 1 RPS pod cost ₹350/day. Same TAT, same throughput, same accuracy envelope. At our traffic shape (50 RPS sustained for the peak hour, 10 RPS for the remaining 23), that translates t… more26 May 2026
Venue
Inmobi, 5th Floor, Nucleus Room
Delta Block, Embassy Tech Square Main Rd, Kaverappa Layout,
Kadubeesanahalli,
Bengaluru - 560103
Karnataka, IN
Loading…
Hosted by
Jumpstart better data engineering and AI futures