The Role
Design, build, and productionize Generative AI, Agentic AI, multi-agent, LLM, and RAG solutions for enterprise cybersecurity products. Responsibilities include AI architecture, agent orchestration, integrations with security systems, evaluation, optimization, secure deployment, monitoring, troubleshooting, and mentoring. The role requires production-quality Python and FastAPI development, cloud deployment, database integration, and independent ownership of initiatives from business problem through continuous improvement.
Summary Generated by Built In
Job Description – Senior AI Engineer (GenAI & Agentic AI)
Location: Hyderabad Experience: 5+ Years Total | 2+ Years Hands-on GenAI & Agentic AI Employment Type: Full-time
About the Role
We are looking for a Senior AI Engineer to drive the design, architecture, development, and productionization of Generative AI, Agentic AI, and AI-driven automation solutions for enterprise cybersecurity products.
The ideal candidate should be able to independently own AI initiatives end-to-end—from understanding the business problem and defining the AI approach to architecture, implementation, integration, evaluation, deployment, monitoring, and continuous improvement. The role requires strong hands-on engineering capability rather than research-only or API-integration experience.
Key Responsibilities
•
Own AI/GenAI initiatives end-to-end, translating business and cybersecurity requirements into scalable AI solutions.
•
Design and implement Agentic AI and Multi-Agent systems for autonomous investigation, decision support, workflow automation, threat analysis, and security operations.
•
Architect and develop LLM-powered applications, RAG pipelines, AI agents, conversational systems, and intelligent automation workflows.
•
Design agent orchestration including planning, tool/function calling, memory, state management, task decomposition, retries, human-in-the-loop, and guardrails.
•
Build enterprise-grade RAG solutions, including document ingestion, preprocessing, chunking, embeddings, vector search, metadata filtering, reranking, and contextual response generation.
•
Integrate AI agents with enterprise and cybersecurity systems through REST APIs, webhooks, SDKs, databases, SIEM/EDR/security tools, & third-party services.
•
Establish AI evaluation mechanisms covering accuracy, relevance, groundedness, hallucination, tool-call accuracy, latency, reliability, & cost.
•
Optimize LLM applications for performance, scalability, reliability, token consumption, latency, and inference cost.
•
Design secure AI solutions addressing prompt injection, data leakage, access control, sensitive information handling, unsafe tool execution, and AI-specific security risks.
•
Develop production-ready AI services and APIs using Python/FastAPI, with appropriate logging, error handling, testing, observability, and monitoring.
•
Independently troubleshoot complex issues across LLM, RAG, agent orchestration, integrations, APIs, databases, and deployment environments.
•
Mentor AI engineers and contribute to AI architecture standards, reusable frameworks, engineering best practices, and technical decision-making.
Must-Have Skills & Experience
AI / GenAI / Agentic AI
•
5+ years total software/engineering experience, with at least 2+ years hands-on experience in GenAI and Agentic AI.
•
Strong practical experience building LLM-based production applications and AI agents.
•
Strong understanding of Agentic AI, Multi-Agent Systems, AI workflows, tool calling/function calling, planning, memory, state management, human-in-the-loop patterns and fine-tuning.
•
Hands-on experience with LangChain and/or LangGraph; experience with CrewAI, AutoGen, Agno, LlamaIndex or similar frameworks is a plus.
•
Strong expertise in RAG architecture, embeddings, vector search, hybrid search, reranking, and knowledge-base design.
•
Hands-on experience with vector databases such as Qdrant, Milvus, Pinecone, Weaviate, Chroma or OpenSearch.
•
Strong prompt engineering skills, including structured outputs, few-shot prompting, prompt optimization, and context engineering.
•
Experience with LLM evaluation, hallucination reduction, guardrails, AI observability, and production monitoring.
•
Experience with LLM providers/models such as OpenAI, Azure OpenAI, Anthropic Claude, Gemini, Llama, Mistral or equivalent.
•
Strong Python programming skills with FastAPI, Pydantic, async programming, REST APIs, and API integration.
•
Working knowledge of SQL/NoSQL databases, preferably MySQL/PostgreSQL
•
Experience with Docker and cloud-based AI deployment, preferably AWS.
•
Strong understanding of Git, CI/CD, testing, debugging, logging, and production support.
Cybersecurity – Preferred
•
Experience building AI solutions for SOC, SIEM, EDR/XDR, vulnerability management, threat intelligence, incident response, or attack surface management.
•
Understanding of CVE/CVSS, MITRE ATT&CK, threat intelligence, security alerts, vulnerabilities, and security operations workflows is highly desirable.
Good to Have
•
Basic understanding of JavaScript/TypeScript, React, and modern web application architecture.
•
Working knowledge of AWS services such as ECS/EKS, Lambda, S3, Bedrock, RDS, OpenSearch, and CloudWatch.
•
Experience with MCP (Model Context Protocol) and modern agent/tool integration patterns.
•
Exposure to LoRA/PEFT, open-source LLMs, model serving, or inference optimization.
Requirements
What We Expect
The successful candidate should be able to take an AI initiative from “business problem → AI approach → architecture → POC → production implementation → evaluation → deployment → monitoring” with minimal supervision.
We are specifically looking for an engineer who can make architecture decisions, write production-quality code, integrate enterprise systems, troubleshoot independently, and continuously improve AI solutions—not someone limited to prompt writing or calling LLM APIs.
Education: B.Tech/B.E./M.Tech in Computer Science, AI/ML, Data Science, or related discipline.
Skills Required
- 5+ years of total software or engineering experience
- 2+ years of hands-on Generative AI and Agentic AI experience
- Experience building production LLM applications and AI agents
- Understanding of Agentic AI, multi-agent systems, AI workflows, tool calling, planning, memory, state management, human-in-the-loop patterns, and fine-tuning
- Hands-on experience with LangChain and/or LangGraph
- Experience with CrewAI, AutoGen, Agno, LlamaIndex, or similar frameworks
- Expertise in RAG architecture, embeddings, vector search, hybrid search, reranking, and knowledge-base design
- Hands-on experience with vector databases such as Qdrant, Milvus, Pinecone, Weaviate, Chroma, or OpenSearch
- Strong prompt engineering skills, including structured outputs, few-shot prompting, prompt optimization, and context engineering
- Experience with LLM evaluation, hallucination reduction, guardrails, AI observability, and production monitoring
- Experience with LLM providers or models such as OpenAI, Azure OpenAI, Anthropic Claude, Gemini, Llama, or Mistral
- Strong Python skills with FastAPI, Pydantic, asynchronous programming, REST APIs, and API integration
- Working knowledge of SQL or NoSQL databases, preferably MySQL or PostgreSQL
- Experience with Docker and cloud-based AI deployment, preferably AWS
- Understanding of Git, CI/CD, testing, debugging, logging, and production support
- Experience building AI solutions for SOC, SIEM, EDR/XDR, vulnerability management, threat intelligence, incident response, or attack surface management
- Understanding of CVE/CVSS, MITRE ATT&CK, threat intelligence, security alerts, vulnerabilities, and security operations workflows
- Basic understanding of JavaScript/TypeScript, React, and modern web application architecture
- Working knowledge of AWS ECS/EKS, Lambda, S3, Bedrock, RDS, OpenSearch, and CloudWatch
- Experience with MCP and modern agent/tool integration patterns
- Exposure to LoRA/PEFT, open-source LLMs, model serving, or inference optimization
- B.Tech, B.E., or M.Tech in Computer Science, AI/ML, Data Science, or a related discipline
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
NopalCyber provides integrated offensive and defensive cybersecurity solutions for organizations seeking resilience and compliance. Its offerings include managed extended detection and response, attack surface management, breach and attack simulation, advisory services, and 24/7 security operations. AI-driven products such as Nopal360°, NopalGo, and Cyber Intelligence Quotient help clients quantify, visualize, and reduce cyber risk across their IT environments while tailored service packages broaden access to enterprise-grade protection.
