AI Security Engineer

Arohana Tech Solutions Private Limited; Bengaluru; On-site; INR 3,500,000 - 5,500,000; Full time

Job summary

Arohana Tech Solutions Private Limited seeks a senior security architect to design secure AI-enabled systems across web, mobile, APIs, and data stores. You will focus on risk mitigation for traditional and AI-specific threats, including prompt-injection and data leakage, while shaping secure RAG pipelines and governance.

The role requires deep experience in security architecture, AI security, and MLOps/LLMOps, with an emphasis on responsible AI, model governance, and auditability in regulated

Qualifications

• 10+ years of software, architecture, data, security or AI engineering experience.
• Experience designing enterprise-grade AI solutions in high-security environments.
• Experience delivering AI solutions from data ingestion to secure deployment and operations.

Responsibilities

• Define secure architectures for web, mobile, APIs, AI services, data stores and integrations.
• Mitigate traditional vulnerabilities and AI-specific risks like prompt injection and data leakage.
• Design secure RAG pipelines with access control, validation, and retrieval security.
• Evaluate LLMs, embeddings, vector databases and graph tech based on security, quality and cost.
• Compare solutions using Neo4j, Pinecone, Weaviate, Milvus, and similar platforms.
• Define production deployment, MLOps/LLMOps, monitoring, drift detection, and rollback strategies.
• Establish Responsible AI, governance, explainability, auditability and human oversight.
• Stay updated on AI security threats and translate learnings into practical controls.

Skills

Application security

API security

Mobile security

Security architecture

AI security

Threat modelling

Prompt injection protection

LLMs, RAG, embeddings

Data governance

IAM, RBAC/ABAC

Kubernetes/OpenShift

Tools

Neo4j

Pinecone

Weaviate

Milvus

Azure AI Search

Chroma

pgvector

Job description

• Define secure application architectures covering web, mobile, APIs, AI services, data stores, models, and enterprise integrations, focusing on Security Flaws, Vulnerabilities & Risks.
• Identify and mitigate traditional application vulnerabilities as well as AI-specific risks such as prompt injection, data leakage, RAG poisoning, model misuse, and excessive agent privileges.
• Design secure RAG pipelines with proper document validation, access control, retrieval security, vector-store protection, and response validation.
• Evaluate and select LLMs, embedding models, rerankers, vector databases, and graph technologies based on security, quality, scale, latency, and cost.
• Compare and design solutions using platforms such as Neo4j, Pinecone, Weaviate, Milvus, Azure AI Search, Chroma, pgvector, or similar technologies.
• Define production deployment, MLOps/LLMOps, model monitoring, evaluation, drift detection, retraining, versioning, and rollback strategies.
• Establish Responsible AI, model governance, explainability, auditability, compliance, and human oversight.
• Stay aware of emerging AI security threats and industry incidents and translate those learnings into practical architecture and security controls.

Responsibilities

Job Description:

• Define secure application architectures covering web, mobile, APIs, AI services, data stores, models, and enterprise integrations, focusing on Security Flaws, Vulnerabilities & Risks.
• Identify and mitigate traditional application vulnerabilities as well as AI-specific risks such as prompt injection, data leakage, RAG poisoning, model misuse, and excessive agent privileges.
• Design secure RAG pipelines with proper document validation, access control, retrieval security, vector-store protection, and response validation.
• Evaluate and select LLMs, embedding models, rerankers, vector databases, and graph technologies based on security, quality, scale, latency, and cost.
• Compare and design solutions using platforms such as Neo4j, Pinecone, Weaviate, Milvus, Azure AI Search, Chroma, pgvector, or similar technologies.
• Define production deployment, MLOps/LLMOps, model monitoring, evaluation, drift detection, retraining, versioning, and rollback strategies.
• Establish Responsible AI, model governance, explainability, auditability, compliance, and human oversight.
• Stay aware of emerging AI security threats and industry incidents and translate those learnings into practical architecture and security controls.

Key Skills

• Application, API, mobile, and Security.
• AI Security, Threat modelling, prompt-injection protection, and secure AI design.
• LLMs, RAG, embeddings, semantic search, hybrid search, GraphRAG, and AI agents.
• Vector and graph databases, including selection and architecture trade-offs.
• Data architecture, data governance, privacy, PII protection, lineage, and access control.
• MLOps/LLMOps, model deployment, model registry, monitoring, drift detection, and evaluation.
• Model selection, benchmarking, hallucination/groundedness evaluation, and production quality controls.
• IAM, RBAC/ABAC, encryption, secrets management, network isolation, and secure SDLC.
• Responsible AI, model governance, bias, explainability, compliance, and auditability.
• Kubernetes/OpenShift, containers, GPUs, model serving, and enterprise observability.
• Strong communication, technical leadership, and architecture decision-making.

Experience

• 10+ years of software, architecture, data, Security or AI engineering experience.
• Experience designing enterprise-grade AI solutions, preferably in regulated, government, banking, telecom, or other high-security environments.
• Experience taking AI solutions from data ingestion and model selection through deployment, monitoring, governance & production operations in a secure manner.

Skills: data architecture,vector database,ai security,llm,rag,generative ai