Senior Staff Engineer (AI Full-stack Developer)

Nagarro; Mumbai; On-site; INR 390,600 - 781,200; Full time

Job summary

jobr.pro is seeking an experienced AI/ML software engineer with 7.5+ years to design and deliver production-grade AI applications. You will build React-based interfaces, backend services in Java or Python, and end-to-end RAG pipelines for embeddings and vector storage.

You will integrate with major LLM providers, implement prompt templates, and build secure, scalable AI solutions for enterprise contexts. Collaborating with security, DevOps, and business teams, you will ensure responsible AI

Qualifications

• Bachelor’s or master’s degree in computer science, information technology, or related field.

Responsibilities

• Design, develop, and deploy AI‑powered applications and intelligent assistants using LLMs to automate security and enterprise workflows.

Skills

React

Java/Python

LLM platforms

RAG pipelines

LangChain/Haystack

Prompt engineering

FastAPI/Flask

HTML/JS/CSS

Git & CI/CD

Docker/Linux

Cloud platforms

Security basics

Responsible AI

Cross-functional

Education

Bachelor's or Master's in CS/IT

Tools

LangChain

LlamaIndex

Kubernetes

Terraform

Bicep

OpenAI API

FastAPI

React

Job description

Job Description

Requirements

• Experience : 7.5+ years
• Relevant experience in software development, AI/ML engineering, or applied AI with hands‑on experience building production‑grade AI applications.
• Strong expertise in React for developing modern, responsive, and interactive web applications.
• Proficiency in Java and/or Python with hands‑on experience building backend services, REST APIs, and AI‑driven applications.
• Experience working with LLM platforms such as OpenAI, Anthropic, Azure OpenAI, or similar foundation models.
• Hands‑on experience designing and implementing Retrieval‑Augmented Generation (RAG) pipelines, including embeddings, vector databases, chunking strategies, retrieval optimization, and grounding techniques.
• Experience with LLM orchestration frameworks such as LangChain, LlamaIndex, LangGraph, Haystack, or equivalent.
• Strong knowledge of prompt engineering, structured outputs, function calling, tool integration, and agentic AI workflows.
• Experience developing AI services using FastAPI, Flask, or similar backend frameworks.
• Knowledge of HTML, CSS, JavaScript, asynchronous programming, testing frameworks, and API development.
• Experience with LLM evaluation frameworks such as RAGAS, DeepEval, Promptfoo, LangSmith, or equivalent.
• Familiarity with Git, CI/CD pipelines, Docker, Linux, and software deployment practices.
• Working knowledge of at least one cloud platform such as Azure, AWS, or GCP.
• Basic understanding of infrastructure security concepts, including vulnerabilities, IAM, logging, access controls, and cloud security best practices.
• Understanding of responsible AI principles, including prompt injection prevention, data privacy, hallucination mitigation, output validation, and content filtering.
• Familiarity with SIEM platforms, security monitoring tools, Infrastructure as Code (Terraform or Bicep), and vulnerability management concepts is an advantage.
• Strong analytical, troubleshooting, communication, and problem‑solving skills with the ability to work collaboratively in cross‑functional teams.
• Relevant cloud, AI, or security certifications are an added advantage.

Responsibilities

• Design, develop, and deploy AI‑powered applications and intelligent assistants using Large Language Models (LLMs) to automate security and enterprise workflows.
• Build scalable React‑based user interfaces and dashboards for AI‑driven applications and enterprise automation solutions.
• Develop backend services, REST APIs, and orchestration layers using Java and/or Python to support AI capabilities.
• Design and implement end‑to‑end Retrieval‑Augmented Generation (RAG) pipelines, including document ingestion, embeddings, vector storage, retrieval optimization, and contextual response generation.
• Integrate enterprise AI solutions with LLM providers such as OpenAI, Anthropic, Azure OpenAI, and other commercial or open‑source models.
• Develop prompt templates, system prompts, structured outputs, and agentic workflows to improve AI accuracy and user experience.
• Build AI microservices and APIs that integrate with enterprise applications, security tools, monitoring platforms, ticketing systems, and operational workflows.
• Implement evaluation frameworks, regression testing, and performance monitoring to continuously improve model quality, latency, reliability, and operational efficiency.
• Apply responsible AI practices by implementing security controls, prompt injection protection, PII masking, access controls, audit logging, and output validation.
• Automate AI operational tasks including data preparation, embedding refresh, model evaluation, health monitoring, and deployment processes.
• Collaborate with engineering, DevOps, infrastructure, security, and business teams to design and deliver scalable AI‑powered solutions.
• Participate in code reviews, testing, debugging, documentation, and production support activities to ensure high‑quality software delivery.
• Continuously evaluate emerging AI technologies, frameworks, and best practices to enhance enterprise AI capabilities and accelerate innovation.
• Ensure AI applications are scalable, secure, maintainable, and aligned with enterprise architecture, governance, and compliance standards.

Qualifications

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