Sreenidhi Nallajerla@sreenidhi-n
1
Events attended
1
Submissions made
India
2+ years of experience
About me
She/Her. I build security into systems that can’t afford to fail. My work sits at the intersection of regulated infrastructure, AI-native products, fintech, and healthcare, environments where the stakes are real and compliance isn’t optional. I currently lead DevSecOps implementation and ABDM-WASA certification efforts at Caladrius Health AI Studio, alongside independent security assessments for teams that value thoroughness over checkbox compliance. Before going independent, I built and integrated vulnerability management tooling, working across CI/CD security, automated scanning, and PII tokenization workflows. I later contributed to investigative tooling initiatives and conducted digital forensics research. I also speak and teach on cybersecurity, with a particular interest in making complex threat landscapes feel more navigable for the people operating inside them. I write as well: on security, emerging threats, and the quieter human questions underneath all of it. You’ll find that at mozartchangedmylife.substack.com Open to security consulting, regulatory compliance engagements, technical writing, and conversations with organisations that prefer taking security seriously before something breaks.
🤓 Latest Submissions
SOCrates
The problem: A new CVE drops every 19 minutes. A senior SOC analyst spends two-plus hours triaging a single critical vulnerability, pulling NVD data, cross-referencing CISA's Known Exploited Vulnerabilities catalog, mapping the kill chain to MITRE ATT&CK, drafting a Sigma detection rule, prioritizing remediation. By the time the report is written, three more zero-days have dropped. This is how SOC analysts burn out in 18 months. The solution: SOCrates is a multi-agent autonomous SOC analyst. You give it a CVE ID. Three specialized AI agents (orchestrated by CrewAI, running on a single AMD Instinct MI300X) produce a full incident response report in under a minute. - Scout:(Llama 3.3 70B) fetches live threat intelligence from the NVD API, checks CISA KEV for active exploitation, and pulls vendor advisory excerpts from Fortinet, Palo Alto, MSRC, and others. - Adversary: (Llama 3.3 70B) simulates the full six-phase kill chain, names the real offensive tools an attacker would use (Sliver, Cobalt Strike, Mimikatz), maps the threat to documented APT groups via MITRE ATT&CK Group profiles, and reasons about CVE chaining. - Coroner: (Qwen 2.5 72B) synthesizes everything into a MITRE ATT&CK–mapped report with a sigma-cli–validated Sigma rule and effort-labeled remediation steps. Target audience: Enterprise SOC teams, MSSPs, security engineers, and CISOs who need to triage CVEs faster without sending sensitive threat intel to external APIs. What's unique: All three 70B-class models live in 192GB of VRAM simultaneously - no model swapping, no cloud round-trips, no per-token billing. SOCrates is on-premises and air-gapped deployable, which is what enterprise security actually requires. Threat intel never leaves your network. Built in 8 days as a solo dev with, on $100 of AMD Developer Cloud credits (thank you!!) and an AI coding assistant :) Stack: CrewAI, Llama 3.3 70B, Qwen 2.5 72B, Ollama, Gradio, NVD API, CISA KEV, MITRE ATT&CK v16, AMD Instinct MI300X.
10 May 2026
