Accepting submissions
Not accepting submissions
Akash Sathish When the agent workflow survives production but the MCP server splits an RCEEvery 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… more
Submission type: Anchor talk (30 mins)
|
|
VK
Vivek Kalyanarangan ₹11 Lakh/Month: How We Took the GPU Out of Face MatchFace 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… more
Submission type: Anchor talk (30 mins)
|
Zahle Making Generative UI work in productionFormat Lightning Talk Speaker Zahle Khan, Founding Engineer, Thesys LinkedIn Twitter more
|
Pravein Govindan Kannan Sovereign LLM Inference on Heterogenous AI Accelerators Using llm-d and vLLMDescription Most production inference clusters today are single-vendor — not because it is optimal, but because it is the simplest way to set things up. Real fleets are accumulating heterogeneity, through procurement cycles, supply constraints, and the widening cost gap between accelerators. The open question is whether a single Kubernetes-native serving layer can take a heterogeneous GPU fleet a… more
Submission type: Lightning talks (10 mins)
|
Nabendu Karmakar Grounding AI Agents in Production: A Practitioner's Implementation GuideSession Description Most enterprise AI agents that fail in production don’t fail because of model quality - they fail because they have no ground beneath them. Without structured semantic context, agents hallucinate over ambiguous schemas, misfire on intent, and produce answers that are technically fluent but operationally wrong. This session walks through the full grounding stack - from semantic… more
Submission type: Anchor talk (30 mins)
|
Ramanuj Vidyanta AI Governance in Indian Banks Isn't a Policy Problem — It's an Engineering Problem{Describe your session in 2 paragraphs} Every major Indian bank now has an AI governance policy document. Most are useless in production. I’ve spent the last several years operationalizing AI governance frameworks — RBI’s FREE AI guidelines, the EU AI Act (for global banking clients), ISO 42001, NIST AI RMF, and the DPDP Act — across production ML systems at some of India’s largest financial inst… more
Submission type: Lightning talks (10 mins)
|
KANIKA SINGHAL When AI Agents Access Your Data: Controlling Data Flow in Modern Pipelines{Describe your session in 2 paragraphs} Modern AI systems increasingly rely on agents and automated workflows that interact with databases, APIs, and external services. While databases like PostgreSQL provide strong controls for who can access data, they do not govern how that data us used once retrieved. In practice, agent-driven pipelines can query sensitive data and then propagate it across sy… more
Submission type: Lightning talks (10 mins)
|
|
r
rajesh 
Sachin Chaurasiya Debugging Agents in ProductionDebugging Agents in Production Every distributed system is impossible to debug without custom built observability and tracing tools. Multi-agent systems are no different. more
Submission type: Anchor talk (30 mins)
|
Asif Mansoor Amanullah Why Data Quality Matters When Working with Data at ScaleMost data quality problems aren’t bugs in the data. They’re broken contracts between producers and consumers. The contract gets implicitly defined when the first staging pipeline runs, then quietly violated in production when an upstream service ships a “harmless” schema change, a field gets nullified, or volume changes by 10x without warning. By the time the dashboards look wrong, the bad data h… more
Submission type: Lightning talks (10 mins)
|
Get your hybrid access ticket
Hosted by
Jumpstart better data engineering and AI futures
Supported by
Venue host
PhonePe was founded in December 2015 and has emerged as India’s largest payments app, enabling digital inclusion for consumers and merchants alike.