Staff Engineer

Nagarro; Navi Mumbai; Vor Ort; INR 2.500.000 - 4.000.000; Vollzeit

Zusammenfassung

Nagarro is seeking a seasoned AI/ML engineer in Navi Mumbai to build production-grade LLM applications and AI assistants. You will own frontend and backend integration using Python, Java, and industry tools, delivering scalable AI features for security, automation, and enterprise workflows.

You will work with LangChain-LlamaIndex-Haystack ecosystems, design robust prompts, and ensure observability and cost control across pipelines.

Qualifikationen

• Solid experience building production-grade LLM applications.
• Strong React.js frontend development experience.
• Proficiency with Python for AI development and integration.

Aufgaben

• Design and deploy LLM-powered features and AI assistants.
• Build backend AI services using Python and Java as needed.
• Integrate OpenAI, Anthropic, Azure OpenAI, and Vertex AI in enterprise apps.
• Develop prompt templates, system prompts, and function-calling workflows.
• Implement end-to-end Retrieval-Augmented Generation (RAG) pipelines.
• Create AI agents with LangChain, LlamaIndex, or Haystack.
• Establish evaluation, observability, and security controls.

Kenntnisse

React.js

Python

Java

LLM platforms

LangChain

RAG pipelines

Vector stores

Cloud platforms

Ausbildung

Bachelor’s or Master’s degree in CS/IT or related field

Tools

LangChain

LlamaIndex

Haystack

Pinecone

Weaviate

FAISS

Docker

Git

CI/CD

Jobbeschreibung

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 39 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!

Job Description

Requirements

• Experience : 5.5+years
• Experience in software development, AI/ML engineering, or applied AI, including at least 1-2 years of hands-on experience building production-grade LLM applications.
• Expert-level proficiency in React.js for developing scalable, responsive, and reusable frontend applications.
• Strong hands-on experience with Python for AI development, automation, backend services, and API integration.
• Working knowledge of Java for backend services, REST API development, and enterprise application integration.
• Practical experience with LLM providers and APIs, including OpenAI, Anthropic, Azure OpenAI, Vertex AI, or equivalent platforms.
• Hands-on experience with prompt engineering, system prompts, structured outputs, JSON schemas, function calling, and tool integration.
• Strong understanding of LLM application development, AI assistants, agentic workflows, and enterprise AI integration.
• Experience with at least one LLM orchestration framework such as LangChain, LlamaIndex, LangGraph, Haystack, or equivalent.
• Hands-on experience implementing RAG pipelines, including embeddings, document chunking, retrieval tuning, grounding, and vector database integration.
• Experience with at least one vector database or search platform, such as pgvector, Pinecone, Weaviate, Chroma, FAISS, Azure AI Search, or Vertex AI Vector Search.
• Working knowledge of LLM evaluation methodologies, including evaluation datasets, regression testing, and frameworks such as RAGAS, DeepEval, Promptfoo, or LangSmith.
• Strong understanding of AI application testing, debugging, observability, performance optimization, and cost management.
• Familiarity with asynchronous programming, Python packaging, testing frameworks, and application development best practices.
• Knowledge of Shell scripting, Linux fundamentals, Git, CI/CD pipelines, and Docker.
• Exposure to at least one cloud platform such as Microsoft Azure, AWS, or Google Cloud Platform.
• Basic understanding of Infrastructure Security concepts, including vulnerabilities, patch management, security logs, IAM, and access controls.
• Awareness of responsible AI and security practices, including prompt injection, data leakage, hallucinations, bias, and content filtering.
• Familiarity with SIEM platforms such as Microsoft Sentinel or Splunk, including the ability to write KQL or SPL queries for AI-assisted security detection and investigation.
• Basic understanding of Cloud Security Posture Management (CSPM) and cloud security controls such as Network Security Groups (NSGs), Web Application Firewalls (WAF), IAM policies, and conditional access.
• Understanding of Infrastructure as Code (IaC) tools such as Terraform or Bicep for cloud-native AI service deployment and configuration.
• Exposure to data privacy and regulatory requirements applicable in India, including the DPDP Act and RBI IT Risk Framework, particularly in handling personal and sensitive data within AI systems.
• Familiarity with vulnerability management concepts, including CVE, CVSS, EPSS scoring, CISA KEV catalogue, and patch prioritization workflows.
• Strong analytical and problem-solving skills, with the ability to debug LLM behavior across prompts, retrieval pipelines, and tool integrations.
• Ability to interpret evaluation metrics, application logs, and security telemetry to improve AI quality, reliability, and operational efficiency.
• Demonstrated ownership of AI solutions from prototype to production, including evaluation, observability, testing, and documentation.
• Strong learning agility and adaptability to evolving AI models, frameworks, tools, and development practices.
• Excellent written and verbal communication skills, with the ability to collaborate effectively across technical and business teams.
• Certifications such as CISSP, Associate of ISC², CEH, Google Professional Machine Learning Engineer, AWS Certified Machine Learning - Specialty, Microsoft Azure Administrator Associate (AZ-104), CCSP, or Google Associate Cloud Engineer are preferred.

Responsibilities

• Design, develop, and deploy LLM-powered features, AI assistants, and intelligent automation solutions to support Infrastructure Security (InfraSec) workflows.
• Build AI-driven capabilities for vulnerability summarization, log triage, remediation recommendations, security policy reviews, configuration assessments, and natural-language querying of security data.
• Build and maintain backend AI services and APIs using Python, with Java-based backend development wherever required.
• Integrate LLM providers such as OpenAI, Anthropic, Azure OpenAI, Vertex AI, and open-source models into enterprise applications.
• Design, develop, and optimize prompt templates, system prompts, structured-output schemas, and function-calling workflows.
• Implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, including document chunking, embeddings, vector store integration, retrieval optimization, and response grounding.
• Develop AI agents and tool-calling workflows using frameworks such as LangChain, LlamaIndex, LangGraph, Haystack, or equivalent technologies.
• Build evaluation frameworks, golden datasets, and regression test suites to measure LLM accuracy, hallucination rates, response quality, latency, and cost.
• Perform prompt engineering and continuously improve AI outputs through offline and online evaluations.
• Implement responsible AI and security controls, including 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 other security infrastructure to enable automated security workflows.
• Automate AI/ML operations activities such as data preparation, embedding refresh, evaluation runs, health checks, and monitoring using Python and Shell scripting.
• Support application testing, debugging, performance tuning, and cost optimization to ensure reliable and scalable AI solutions.
• Maintain technical documentation, source code repositories, deployment artifacts, and operational procedures.
• Collaborate with security, infrastructure, engineering, DevOps, and data teams to translate business requirements into practical AI-driven solutions.
• Apply infrastructure security principles and cloud security controls while designing and deploying AI services.
• Continuously evaluate emerging LLM models, frameworks, prompting techniques, and evaluation methodologies to improve solution quality and security posture.

Qualifications

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