AI-Powered Cybersecurity Platform
Budget: ₹12,500 – ₹37,500 INR
Project Overview:
>We are developing a next-generation AI-powered cybersecurity platform to enhance threat detection, security operations, incident response, and intelligent decision-making through Agentic AI and Generative AI. Our objective is to build an enterprise-grade, production-ready AI ecosystem that goes beyond traditional chatbots by enabling autonomous AI agents capable of reasoning, planning, executing multi-step tasks, and securely interacting with cybersecurity tools and knowledge sources.
>The platform will leverage Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and domain-specific cybersecurity knowledge to provide intelligent assistance for SOC analysts, security engineers, and incident responders. The solution must deliver accurate, low-latency responses while integrating seamlessly with our existing cybersecurity infrastructure and services.
>The selected AI/ML Engineer will be responsible for the complete AI lifecycle—from data engineering and model development to deployment, optimization, and production integration. This includes designing scalable data pipelines, developing RAG workflows, fine-tuning or optimizing LLMs using private cybersecurity datasets, implementing autonomous AI agents, and exposing secure APIs for integration with our backend and frontend applications.
Key Responsibilities:
>Design, develop, and deploy production-ready AI solutions using Agentic AI, Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG).
>Build scalable data ingestion and vector database pipelines for cybersecurity knowledge retrieval.
>Fine-tune, optimize, and evaluate LLMs using proprietary cybersecurity datasets to improve domain-specific accuracy.
>Develop autonomous AI agents capable of multi-step reasoning, planning, tool invocation, and workflow automation.
>Integrate AI services with existing cybersecurity platforms through RESTful APIs or gRPC services.
>Optimize inference performance, latency, scalability, and operational costs for production environments.
>Collaborate with backend, frontend, DevOps, and cybersecurity teams to deliver seamless AI integration.
>Implement secure deployment pipelines, monitoring, logging, and model lifecycle management.
>Maintain clean, modular, and well-documented code following software engineering best practices.
Key Deliverables:
>Scalable cybersecurity data ingestion and vector database pipeline supporting RAG workflows.
>Production-ready, fine-tuned, or optimized LLMs meeting defined accuracy and latency requirements.
>Agentic AI framework supporting autonomous reasoning, multi-step decision-making, and tool execution.
>Secure AI service layer exposing REST/gRPC APIs for enterprise application integration.
>Production-ready deployment scripts, CI/CD pipelines, and infrastructure automation.
>Comprehensive documentation covering architecture, deployment, APIs, and operational procedures.
>End-to-end integration with the organization's cybersecurity platform in staging and production environments.
Acceptance Criteria:
>Fully reproducible training, fine-tuning, and inference pipelines.
>AI models achieve agreed accuracy, latency, and reliability benchmarks.
>Secure, scalable, and production-ready deployment using automated CI/CD workflows.
>Successful integration with existing cybersecurity services and applications.
>Comprehensive automated testing, monitoring, and logging implemented across the AI platform.
>Well-documented architecture, APIs, and deployment procedures.
Preferred Technical Skills:
>Strong expertise in Python and AI/ML development.
>Hands-on experience with Agentic AI frameworks (LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, or similar).
>Experience building Generative AI and Retrieval-Augmented Generation (RAG) applications.
>Fine-tuning and optimization of Large Language Models (LLMs).
>Experience with vector databases such as Pinecone, Milvus, Weaviate, FAISS, or ChromaDB.
>Knowledge of LangChain, LlamaIndex, and AI orchestration frameworks.
>Strong understanding of PyTorch, Hugging Face Transformers, and model optimization techniques.
>Experience deploying AI workloads on AWS (EKS, SageMaker, EC2, Bedrock, or equivalent cloud services).
>Experience designing RESTful APIs, gRPC services, Docker, Kubernetes, and CI/CD pipelines.
>Familiarity with cybersecurity concepts such as SIEM, SOC operations, threat intelligence, vulnerability management, and incident response is highly desirable.
>We are developing a next-generation AI-powered cybersecurity platform to enhance threat detection, security operations, incident response, and intelligent decision-making through Agentic AI and Generative AI. Our objective is to build an enterprise-grade, production-ready AI ecosystem that goes beyond traditional chatbots by enabling autonomous AI agents capable of reasoning, planning, executing multi-step tasks, and securely interacting with cybersecurity tools and knowledge sources.
>The platform will leverage Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and domain-specific cybersecurity knowledge to provide intelligent assistance for SOC analysts, security engineers, and incident responders. The solution must deliver accurate, low-latency responses while integrating seamlessly with our existing cybersecurity infrastructure and services.
>The selected AI/ML Engineer will be responsible for the complete AI lifecycle—from data engineering and model development to deployment, optimization, and production integration. This includes designing scalable data pipelines, developing RAG workflows, fine-tuning or optimizing LLMs using private cybersecurity datasets, implementing autonomous AI agents, and exposing secure APIs for integration with our backend and frontend applications.
Key Responsibilities:
>Design, develop, and deploy production-ready AI solutions using Agentic AI, Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG).
>Build scalable data ingestion and vector database pipelines for cybersecurity knowledge retrieval.
>Fine-tune, optimize, and evaluate LLMs using proprietary cybersecurity datasets to improve domain-specific accuracy.
>Develop autonomous AI agents capable of multi-step reasoning, planning, tool invocation, and workflow automation.
>Integrate AI services with existing cybersecurity platforms through RESTful APIs or gRPC services.
>Optimize inference performance, latency, scalability, and operational costs for production environments.
>Collaborate with backend, frontend, DevOps, and cybersecurity teams to deliver seamless AI integration.
>Implement secure deployment pipelines, monitoring, logging, and model lifecycle management.
>Maintain clean, modular, and well-documented code following software engineering best practices.
Key Deliverables:
>Scalable cybersecurity data ingestion and vector database pipeline supporting RAG workflows.
>Production-ready, fine-tuned, or optimized LLMs meeting defined accuracy and latency requirements.
>Agentic AI framework supporting autonomous reasoning, multi-step decision-making, and tool execution.
>Secure AI service layer exposing REST/gRPC APIs for enterprise application integration.
>Production-ready deployment scripts, CI/CD pipelines, and infrastructure automation.
>Comprehensive documentation covering architecture, deployment, APIs, and operational procedures.
>End-to-end integration with the organization's cybersecurity platform in staging and production environments.
Acceptance Criteria:
>Fully reproducible training, fine-tuning, and inference pipelines.
>AI models achieve agreed accuracy, latency, and reliability benchmarks.
>Secure, scalable, and production-ready deployment using automated CI/CD workflows.
>Successful integration with existing cybersecurity services and applications.
>Comprehensive automated testing, monitoring, and logging implemented across the AI platform.
>Well-documented architecture, APIs, and deployment procedures.
Preferred Technical Skills:
>Strong expertise in Python and AI/ML development.
>Hands-on experience with Agentic AI frameworks (LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, or similar).
>Experience building Generative AI and Retrieval-Augmented Generation (RAG) applications.
>Fine-tuning and optimization of Large Language Models (LLMs).
>Experience with vector databases such as Pinecone, Milvus, Weaviate, FAISS, or ChromaDB.
>Knowledge of LangChain, LlamaIndex, and AI orchestration frameworks.
>Strong understanding of PyTorch, Hugging Face Transformers, and model optimization techniques.
>Experience deploying AI workloads on AWS (EKS, SageMaker, EC2, Bedrock, or equivalent cloud services).
>Experience designing RESTful APIs, gRPC services, Docker, Kubernetes, and CI/CD pipelines.
>Familiarity with cybersecurity concepts such as SIEM, SOC operations, threat intelligence, vulnerability management, and incident response is highly desirable.