2 days ago
Mumbai, IndiaStaff+
Responsibilities
- Design, develop, and deploy LLM-powered features, AI assistants, and intelligent automation for Infrastructure Security workflows.
- Build AI capabilities for vulnerability summarization, log triage, remediation recommendations, security policy reviews, configuration assessments, and natural-language security-data queries.
- Develop scalable frontend applications and dashboards using React.js, JavaScript, HTML, and CSS.
- Build backend AI services and APIs using Python, with Java development where required.
- Integrate commercial and open-source LLM providers into enterprise applications.
- Design prompt templates, system prompts, structured-output schemas, function-calling workflows, and tool integrations.
- Implement and optimize RAG pipelines using document chunking, embeddings, vector stores, retrieval tuning, and response grounding.
- Develop AI agents and tool-calling workflows with LLM orchestration frameworks.
- Build evaluation frameworks, golden datasets, and regression suites measuring accuracy, hallucination rates, response quality, latency, and cost.
- Implement prompt-injection protection, PII redaction, output filtering, rate limiting, audit logging, and access management.
- Integrate AI services with vulnerability scanners, ticketing platforms, SIEM solutions, monitoring tools, and security infrastructure.
- Automate data preparation, embedding refreshes, evaluation runs, health checks, and monitoring using Python and Shell scripting.
- Support testing, debugging, performance tuning, cost optimization, documentation, repositories, deployment artifacts, and operational procedures.
- Collaborate with security, infrastructure, engineering, DevOps, and data teams to deliver AI-driven solutions.
- Apply infrastructure and cloud security controls and evaluate emerging LLM models, frameworks, prompting techniques, and evaluation methods.
Requirements
- At least 5.5 years of experience in software development, AI/ML engineering, or applied AI.
- At least 1–2 years of hands-on experience building production-grade LLM applications.
- Expert proficiency with React.js and strong hands-on Python experience for AI development, automation, backend services, and API integration.
- Working knowledge of Java for backend services and enterprise application integration.
- Experience with LLM providers and APIs such as OpenAI, Anthropic, Azure OpenAI, and Vertex AI, or equivalent platforms.
- Experience with prompt engineering, system prompts, structured outputs, JSON schemas, function calling, tool integration, AI assistants, agentic workflows, and enterprise AI integration.
- Experience with an orchestration framework such as LangChain, LlamaIndex, LangGraph, or Haystack.
- Hands-on RAG experience including embeddings, document chunking, retrieval tuning, grounding, and vector database integration.
- Experience with a vector database or search platform such as pgvector, Pinecone, Weaviate, Chroma, FAISS, Azure AI Search, or Vertex AI Vector Search.
- Knowledge of LLM evaluation methodologies, evaluation datasets, regression testing, and tools such as RAGAS, DeepEval, Promptfoo, or LangSmith.
- Knowledge of AI application testing, debugging, observability, performance optimization, and cost management.
- Basic frontend knowledge of HTML, CSS, and JavaScript and backend API development with FastAPI or Flask.
- Familiarity with asynchronous programming, Python packaging, testing frameworks, and application development practices.
- Knowledge of Shell scripting, Linux, Git, Docker, and cloud platforms such as Microsoft Azure, AWS, or Google Cloud Platform.
- Understanding of infrastructure security, vulnerabilities, patch management, security logs, IAM, access controls, responsible AI, prompt injection, data leakage, hallucinations, bias, and content filtering.
- Familiarity with Microsoft Sentinel or Splunk and the ability to write KQL or SPL queries for security detection and investigation.
- Understanding of CSPM, Network Security Groups, Web Application Firewalls, IAM policies, conditional access, Terraform, or Bicep.
- Exposure to India’s DPDP Act and RBI IT Risk Framework and familiarity with CVE, CVSS, EPSS, the CISA KEV catalogue, and patch prioritization workflows.
- Bachelor’s or master’s degree in computer science, information technology, or a related field.
- Preferred certifications include CISSP, Associate of ISC², CEH, Google Professional Machine Learning Engineer, AWS Certified Machine Learning – Specialty, Microsoft Azure Administrator Associate (AZ-104), CCSP, and Google Associate Cloud Engineer.
Tech Stack
Categories
About Nagarro
Nagarro provides digital engineering and IT consulting services to enterprises, delivering custom software development, cloud modernization, data and analytics, IoT, and digital commerce solutions. Its business model centers on project-based and managed services across the full product lifecycle, from strategy and design to build and operations. Nagarro is a public company headquartered in Munich and listed on the Frankfurt Stock Exchange, with global delivery across multiple regions.