Based in San Francisco, California. Available nationwide, open to relocation.

I write the controls, then I write the code that tests them.

At KPMG I spent two years on IT audit, third-party risk, cloud and IAM review, and SIEM and DLP validation across seven regulated financial institutions. Since then I have been building the automation for that work: an LLM audit agent at Avaly.AI running 227 controls, a CI/CD pipeline that blocks vulnerable code at merge, and a 30-control framework for LLM systems out of my thesis.

GRC and IT audit Third-party risk AI security DevSecOps Detection and response
0

compliance controls operationalized in a production audit agent

0

of manual audit effort removed by automating evidence collection

0

control gaps driven to closure across regulated institutions

0

CVEs caught before production, all remediated to zero

0

less manual phishing triage through an ML classifier

How I work

The path a control takes from framework to closed evidence.

A requirement arrives as prose. It leaves as a scored finding with an artifact attached, and that artifact becomes the audit record. This is the loop I automated at Avaly.AI, and the reason a second audit costs less than the first.

Evidence store, mapped and reusable Framework NIST AI RMF, ISO 42001 Control library 30 controls, 6 domains Evidence Collected automatically Validation Scored 0 to 5
FrameworkNIST AI RMF, ISO/IEC 42001
Control library30 controls across 6 domains
EvidenceCollected automatically
ValidationScored 0 to 5
Evidence storeMapped, reusable, audit ready

Scoring is anchored to the NIST SP 800-53A evidence hierarchy, so two frameworks asking for the same thing never make you collect it twice.

Selected work

Six things I would want to walk you through.

Problem first, then what I built, then what it changed. If a claim has a number on it, I can show you the workpaper, the repo or the paper behind it.

Avaly.AIJun to Aug 2025AI Security Engineer

A compliance team that could not keep up with the product it was governing.

The problemAn early stage AI company needed to show governance across hundreds of controls, with evidence collection done by hand. Manual assessment does not scale next to a product shipping weekly, and the gap between what the policy claimed and what the system did was widening.

What I builtAn LLM Audit Agent in Python and FastAPI, containerized with Docker and deployed through GitHub Actions CI/CD, automating evidence collection, control validation and compliance documentation across 227 controls mapped to NIST AI RMF and ISO/IEC 42001.

The security work alongside itStructured OWASP LLM Top 10 threat modeling across five core product workflow stages, plus two internal tabletop exercises simulating model misuse, unreliable output and sensitive data exposure.

  • 10+ exploitable LLM attack vectors surfaced and 12+ safeguards shipped, including prompt injection, evidence tampering and sensitive data exposure, each mapped to a NIST AI RMF or ISO/IEC 42001 control
  • Tabletops produced defined escalation paths and response ownership for high-risk AI scenarios, which the team did not have before
  • GenAI vendor assessment standardized across 7 trustworthiness domains, adopted as the company process for new vendor onboarding
KPMG IndiaJan 2023 to Jul 2024Cybersecurity Analyst7 regulated institutions

Audit at scale, where every finding has a regulator attached to it.

The workRisk-based technology audit across RBI and SEBI regulated financial institutions: scoping, control walkthroughs, test plan development, fieldwork, issue validation and remediation follow-up spanning cloud, IAM, network, Windows, datacenter and SDLC environments.

Where the value landedThe deliverables outlived the engagements. Remediation dashboards and risk registers became each client's primary mechanism for tracking observation closure, and five policies I authored were accepted at CISO level and referenced in later supervisory reviews.

  • Control maturity elevated from 2.5 to 3.8 ahead of supervisory review, driving 80+ identified gaps to remediation against NIST CSF, ISO 27001 and RBI mandates
  • 35+ audit workpapers prepared and reviewed, documenting testing procedures, evidence and conclusions
  • 5 enterprise policies accepted at CISO level across Asset Management, Change Management, BCP/DR, Security Awareness and Tabletop Exercises
  • 10+ identity and access governance gaps surfaced across 5 Active Directory environments
  • 20+ SDLC and change management control tests across 4 engagements, producing 8+ formal observations for management action
  • Cloud security assessed across AWS, Azure and GCP at 4 institutions, plus 8+ network gaps found across 3 institutions in firewall, NAC and segmentation controls
  • RSA Archer GRC deployed at 2 institutions, configuring assessment templates and remediation workflows that became the auditable reporting record
Third-party riskKPMG7 engagements

Vendor assessments owned from scoping through remediation closure.

The workThird-party and vendor security assessments across regulated institutions. I led pre-assessment preparation and scoping, collected and reviewed vendor documentation and playbooks, identified gaps, then took remediation discussions directly to service providers rather than handing a report over the fence.

What made it workRelationship management, honestly. Assessment readiness depends on vendor managers and service providers actually answering, so I kept the communication line open from kickoff through closure and handled the information security requirement questions myself.

  • Assessed controls spanning infrastructure, access management, physical security, application security, change management and business continuity
  • Datacenter walkthroughs covering physical access governance and Windows event-log monitoring
  • Risk observations escalated to client security teams and KPMG leadership, then tracked through closure
M.S. thesis and research2025 to 2026Under review, ICSE 2027

An auditor can read NIST AI RMF cover to cover and still not know what to test.

The problemNIST AI RMF and ISO/IEC 42001 say what outcomes to achieve. Neither says what evidence proves it or what a failing control looks like. Teams shipping LLM features get asked to demonstrate governance with nothing concrete to demonstrate against.

What I builtA 30-control framework cross-mapped across NIST AI RMF, ISO/IEC 42001 and OWASP LLM Top 10 (2025), anchored to a 0 to 5 maturity model, then a browser-based audit agent that runs it.

  • 81.1% agent-to-human agreement against a 72.2% inter-assessor baseline, which is the more interesting number: assessor disagreement is the real bottleneck in audit
  • Research paper under peer review at ICSE 2027, with a second submission in preparation for IEEE CSF 2027
SecurePipeMar 2026DevSecOps

Tooling that reports findings changes nothing. Tooling that blocks merges changes behavior.

What I builtA GitHub Actions pipeline across a Python Flask application with Bandit for SAST, Semgrep, pip-audit for SCA and OWASP ZAP for DAST, running on every commit. Branch protection requires all five pipeline jobs to pass before anything merges to main.

  • 16 CVEs across 4 packages including denial of service, path traversal and sandbox escape, all eliminated through targeted version remediation
  • 2 high-severity findings reduced to zero: command injection (CWE-78), debug mode remote code execution (CWE-94), SQL injection (CWE-89) and a hardcoded secret (CWE-259)
SOC analyst capstone2026Detection engineering

You cannot judge detection coverage without generating the telemetry yourself.

What I builtA phishing-to-credential-dump attack chain simulated end to end in an isolated VirtualBox lab, Windows 10 victim against a Kali attacker running Metasploit, with Sysmon and Winlogbeat producing telemetry across the kill chain. Then I wrote the detections for it.

  • Detection rules authored in Elastic SIEM and Sigma, mapped to MITRE ATT&CK T1566, T1059 and T1003, with alert fidelity validated against generated activity
  • Full analyst workflow run end to end: log ingestion, alert triage, forensic pivoting, IOC identification, containment documentation and formal incident reporting
Beyond the resume

The parts a one-page PDF cuts.

A resume rewards compression. These are the answers I would give if you asked in an interview. Open whichever one matters for your role.

Also built

Smaller, but they are why engineers talk to me directly.

No translator needed in either direction.

InboxGuard

ML phishing classifier over 10K+ emails at 95% accuracy, catching AI-generated spoofing and brand impersonation.

MyCarePortal

HIPAA Security Rule readiness assessment across 12 threats and three safeguard categories, with a Streamlit dashboard turning requirements into readable scoring.

Inline-Proxy

A transparent proxy that evaluates policy on every agent tool call before it executes, so MCP integrations have a control point that can be audited.

WiCyS President

Grew the UW Bothell chapter from 60 to 80 students leading an 8-member exec team, running CTF nights, phishing simulations and industry panels.

Coverage

Pick the track you are hiring for.

Each one shows how I would describe the work, where it shows up, and what I am hands on with versus what I only have working knowledge of.

Certifications

CompTIA Security+ISO/IEC 27001 AssociateCISA, exam scheduled September 2026AWS Certified AI Practitioner, in progressMulti-Cloud Red Team Analyst, Cyberwarfare LabsEC-Council Network Defense EssentialsEC-Council Ethical Hacking EssentialsCTF winner, UWB GreyHats

Foundational, not hands on

FedRAMP, DPIA, NYDFS 23 NYCRR 500, ISO 27701 and NIS2. I know the shape of each and would get productive quickly, but I have not owned one end to end. I would rather tell you that now than in week three.

Education

Where the engineering half came from.

The master's is where the thesis, the audit agent and the DevSecOps work all happened, so it is less a credential than a two-year build log.

M.S. Cybersecurity Engineering

University of Washington Bothell

2024 to 2026GPA 3.7Thesis: 30-control AI compliance framework

B.Tech, Information Technology

SNDT Women's University, Mumbai

2019 to 2023GPA 3.54

First 90 days

What I would actually own.

Every portfolio describes the past. This is the part a hiring manager is really trying to work out.

Take the audit off your engineers' desks

Evidence collection, control testing and gap tracking through a full SOC 2 or ISO 27001 cycle, pulling engineering in only where human judgment is genuinely needed.

Clear the vendor queue

Third-party assessments from scoping through remediation closure, with a scoring and evidence standard applied consistently, so vendor reviews stop being the thing that blocks deals.

Give your AI features a control set

Threat modeling on the LLM workflows you already ship, plus a testable control library mapped to whichever framework your customers keep asking about, with defined evidence per control instead of a policy PDF.

Contact

If any of that maps to a problem on your team, let's talk.

I am open to security roles across GRC and IT audit, third-party risk, AI governance, security engineering and detection. If you are not sure which bucket I fit, that is usually a good sign. Email is fastest and I answer everything.

Email me Resume LinkedIn GitHub Writing

Resume

One page, current, and the same story as this site in compressed form.

Short link for applications and email signatures: saniyabhaladhare.me/resume