Sr. AI Developer Engineer – ArchSec (L3)

Theomnihire; Mumbai; On-site; INR 300,000 - 550,000; Full time

Job summary

Theomnihire seeks a Sr. AI Developer Engineer – ArchSec (L3) for a hands-on role focused on building, deploying, and optimizing AI-powered tools to accelerate security architecture reviews and risk assessments.

You will pioneer LLM-powered threat modeling assistants and ML models for architecture pattern analysis, collaborating with security architects and a lead engineer. Responsibilities include developing NLP pipelines for SAR intake, implementing RAG-guided guidance over security standards,

Qualifications

• 4–6 years of total relevant experience in AI/ML development, NLP engineering, or AI security tools.

Responsibilities

• AI Threat Modeling Tools: Build and maintain LLM-powered assistants that auto-generate Data Flow Diagrams (DFDs), enumerate threats using STRIDE and PASTA, and recommend mitigating security controls for proposed systems.
• Architectural Risk ML Models: Develop ML models to analyze architecture design documents, cloud resource configurations, and network diagrams to detect deviations from approved security baselines and highlight risky architectural patterns.
• NLP Intake & Classification Pipelines: Build robust NLP pipelines to parse Security Architecture Review (SAR) intake submissions, classify incoming projects by risk domain, and auto-populate review report templates for security teams.
• Architecture & Compliance RAG Pipelines: Implement Retrieval-Augmented Generation (RAG) over internal security standards, regulatory frameworks (ISO 27001, NIST CSF, CIS Benchmarks), and approved enterprise design patterns to provide real-time contextual guidance to architects.
• Agentic Workflows: Develop agentic AI workflows for automated risk scoring by ingesting design artifacts, querying enterprise knowledge bases, computing risk scores, and generating actionable remediation reports.
• Prompt Engineering & Evaluation: Design, test, and evaluate specialized prompts and fine-tuned models for domain-specific tasks, including attack surface enumeration, zero-trust gap analysis, blast radius estimation, and architecture risk summarization.

Skills

AI/ML development

NLP engineering

Prompt engineering

LangChain

LlamaIndex

Education

B.Tech / M.Tech / MCA in CS/IT/AI/ML

Tools

Python

Vector databases

NLP libraries

Agentic workflow frameworks

Cloud security basics

Job description

Job Title: Sr. AI Developer Engineer – ArchSec (L3)

Working Hours: 9:00 AM – 6:00 PM

Mode of Interview: Face-to-Face or MS Teams

Position Summary

The Sr. AI Developer Engineer – ArchSec is a hands-on technical role focused on building, deploying, and optimizing AI-powered tools to accelerate security architecture reviews, threat modeling, and enterprise risk assessments. Working under the direction of the Lead Engineer and in close collaboration with security architects, you will pioneer LLM-powered threat modeling assistants, specialized ML models for architecture pattern analysis, and intelligent automation pipelines for risk report generation.

Requirements

Key Responsibilities

AI Threat Modeling Tools: Build and maintain LLM-powered assistants that auto-generate Data Flow Diagrams (DFDs), enumerate threats using frameworks like STRIDE and PASTA, and recommend mitigating security controls for proposed systems.

Architectural Risk ML Models: Develop ML models to analyze architecture design documents, cloud resource configurations, and network diagrams to detect deviations from approved security baselines and highlight risky architectural patterns.

NLP Intake & Classification Pipelines: Build robust NLP pipelines to parse Security Architecture Review (SAR) intake submissions, classify incoming projects by risk domain, and auto-populate review report templates for security teams.

Architecture & Compliance RAG Pipelines: Implement Retrieval-Augmented Generation (RAG) over internal security standards, regulatory frameworks (ISO 27001, NIST CSF, CIS Benchmarks), and approved enterprise design patterns to provide real-time contextual guidance to architects.

Agentic Workflows: Develop agentic AI workflows for automated risk scoring by ingesting design artifacts, querying enterprise knowledge bases, computing risk scores, and generating actionable remediation reports.

Prompt Engineering & Evaluation: Design, test, and evaluate specialized prompts and fine-tuned models for domain-specific tasks, including attack surface enumeration, zero-trust gap analysis, blast radius estimation, and architecture risk summarization.

Experience: 4–6 years of total relevant experience in AI/ML development, NLP engineering, or AI security tools .

Education: B.Tech, M.Tech, or MCA in Computer Science, Information Technology, AI/ML, or a related field .

Certifications: CompTIA Security+, Certified Ethical Hacker (CEH), CCSP, or Microsoft Security Operations Analyst (SC-200) .

Technical Skills: LLM frameworks (LangChain, LlamaIndex), RAG architecture, vector databases, Python, NLP libraries, agentic workflow frameworks, and cloud security basics.