Senior Staff Engineer (AI Developer InfraSec Automation)

Company Description

We're Nagarro. We are a Digital Product Engineering company that is scaling in a big way! We build products, services, and experiences that inspire, excite, and delight. We work at a scale — across all devices and digital mediums, and our people exist everywhere in the world (18500+ experts across 40 countries, to be exact). Our work culture is dynamic and non-hierarchical. We are looking for great new colleagues. That is where you come in!

Requirements

Experience

• 7.5+ years
• Strong experience in software engineering, AI/ML development, or applied AI, including experience in building production-grade LLM-based applications

Programming & Development

• Strong programming expertise in Python for AI development and automation with hands-on experience in FastAPI or Flask, asynchronous programming, testing frameworks, and package management
• Working knowledge of Java for backend service development and REST API implementation
• Basic frontend development skills using HTML, CSS, and JavaScript

AI/LLM Technologies

• Experience working with LLM providers such as OpenAI, Azure OpenAI, Anthropic, Vertex AI, or similar AI platforms
• Hands-on experience with LLM orchestration frameworks such as LangChain, LlamaIndex, LangGraph, Haystack, or equivalent
• Strong understanding of prompt engineering, structured outputs, JSON schema, function calling, and AI tool orchestration
• Practical experience designing and implementing Retrieval-Augmented Generation (RAG) pipelines using embeddings, chunking strategies, retrieval optimization, and vector databases such as Pinecone, FAISS, Chroma, Weaviate, pgvector, Azure AI Search, or Vertex AI Vector Search
• Experience evaluating LLM performance using frameworks such as RAGAS, DeepEval, Promptfoo, LangSmith, or similar evaluation platforms

Infrastructure & DevOps

• Strong understanding of Linux, Shell scripting, Git, Docker, CI/CD pipelines, and software deployment practices
• Experience working with at least one major cloud platform such as Microsoft Azure, AWS, or Google Cloud Platform
• Familiarity with Infrastructure as Code tools such as Terraform or Bicep

Security & Compliance

• Basic understanding of infrastructure security concepts including vulnerabilities, patch management, logging, identity and access management, and security controls
• Familiarity with AI safety concepts including prompt injection attacks, hallucination prevention, data privacy, bias mitigation, and responsible AI practices
• Understanding of Cloud Security Posture Management (CSPM), cloud security controls, IAM policies, WAF, NSGs, and conditional access concepts
• Understanding of vulnerability management concepts including CVE, CVSS, EPSS, CISA KEV, and patch prioritization processes
• Awareness of data privacy regulations such as the Digital Personal Data Protection (DPDP) Act and enterprise data governance practices

Additional Skills

• Strong analytical, problem-solving, and debugging skills with the ability to troubleshoot AI models, retrieval pipelines, and security workflows
• Excellent written and verbal communication skills with the ability to collaborate effectively across cross-functional teams

Education

• Bachelor's degree in Computer Science, Information Technology, Engineering, or a related discipline

Preferred

• Experience integrating AI solutions with SIEM platforms such as Microsoft Sentinel or Splunk and writing KQL or SPL queries
• Professional certifications such as CISSP (Associate), CEH, CCSP, Google Professional Machine Learning Engineer, AWS Machine Learning Specialty, Azure Administrator (AZ-104), or equivalent cloud and security certifications

Responsibilities

• Design, develop, and deploy AI-powered automation solutions to enhance infrastructure security workflows, including vulnerability summarization, log analysis, remediation recommendations, policy reviews, and natural language querying of security data
• Build and optimize LLM-powered AI assistants using prompt engineering, structured outputs, system prompts, and function-calling capabilities
• Design, implement, and maintain end-to-end Retrieval-Augmented Generation (RAG) pipelines, including chunking strategies, embeddings, vector database integration, retrieval optimization, and grounding techniques
• Develop scalable AI services and REST APIs using Python frameworks such as FastAPI or Flask, integrating with commercial and open-source LLM providers
• Build backend services in Java and lightweight frontend components using HTML, CSS, and JavaScript to support AI-driven internal applications and dashboards
• Develop evaluation frameworks, regression test suites, and benchmark datasets to measure LLM accuracy, latency, hallucination rates, and operational costs
• Implement responsible AI practices, including prompt injection protection, PII masking, output filtering, access controls, audit logging, and rate limiting
• Integrate AI solutions with enterprise security tools, vulnerability scanners, SIEM platforms, monitoring systems, and ticketing applications to automate security operations
• Automate AI operational activities including data preparation, embedding refresh, health monitoring, evaluation runs, and deployment processes using Python and Shell scripting
• Test, troubleshoot, optimize, and maintain AI applications to ensure reliability, scalability, performance, and cost efficiency
• Collaborate with infrastructure, security, DevOps, engineering, and data teams to translate business requirements into production-ready AI solutions
• Maintain technical documentation, code repositories, deployment artifacts, API documentation, and operational runbooks
• Continuously evaluate emerging AI technologies, frameworks, and best practices to improve solution quality, security, and developer productivity

Qualifications

Bachelor's or master's degree in computer science, Information Technology, or a related field.

Service Region

South Asia