Generative AI Engineer

IRISS, Inc.

Bengaluru

On-site

INR 1,400,000 - 2,200,000

Full time

5 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

IRISS, Inc. in Bengaluru, India seeks a Generative AI Engineer to design, build, and deploy AI-powered applications that transform enterprise data into actionable insights.

You will craft conversational analytics platforms enabling natural language questions to yield secure, accurate dashboards, reports, and visualizations. Collaborating with backend/frontend teams, you will work with LLMs, RAG, and data integration in a multi-tenant SaaS/IOT setting, focusing on production-ready AI services on

Qualifications

  • 5+ years of relevant experience including 3+ years deploying AI-powered apps or chatbots.
  • Bachelor's or Master's in CS/Data Science or related field.
  • Experience integrating LLMs using OpenAI, Anthropic, Bedrock, or Hugging Face.
  • Experience with RAG and vector search using embeddings.
  • Strong prompts, orchestration, validation, and conversational workflows.
  • Hands-on AWS with Bedrock, Kendra, OpenSearch, ECS, Lambda, CloudWatch.
  • SQL, multi-tenant data security, and data integration basics.
  • Docker, CI/CD, and microservices experience.

Responsibilities

  • Design, develop, and maintain enterprise-grade generative AI apps and conversational analytics.
  • Build end-to-end conversational AI workflows with NLU, retrieval, SQL generation, validation, and responses.
  • Integrate LLMs via platforms like OpenAI, Anthropic, Bedrock, Hugging Face.
  • Develop prompts, orchestration, and response validation mechanisms.
  • Implement multi-turn conversations with contextual memory and state management.
  • Evaluate AI model performance and improve accuracy, reliability, and efficiency.

Skills

Python development
AI/ML skills
Natural language processing
API development

Education

Bachelor's/Master's in CS/Software/Data Science

Tools

OpenAI
Amazon Bedrock
Hugging Face
LangChain
FAISS/OpenSearch

Job description

IRISS is a global leader in industrial safety and condition-based monitoring technologies, trusted by power generation, data center, and critical infrastructure teams worldwide.

Headquartered in the United States, with manufacturing operations in Bradenton, Florida, and a global presence across LATAM, EMEA, APAC, and India, IRISS develops innovative solutions that make maintenance safer, smarter, and more connected.

Our technologies help organizations prevent equipment failures, reduce operational risks, improve reliability, and protect their people.

At the heart of everything we do is our guiding principle: We Humanize Safety.

We are committed to developing advanced, intuitive technologies that empower people and transform how industries approach safety and reliability.

About the Role

IRISS is seeking an experienced and innovative Generative AI Engineer to join our technology team in Bengaluru, India.

This position will play a critical role in designing, developing, and deploying AI-powered applications that transform complex enterprise data into meaningful, actionable business insights.

You will help build a conversational analytics platform that enables users to ask questions in natural language and receive accurate, secure, and understandable answers through dashboards, reports, and data visualizations.

Working closely with backend engineers, frontend developers, and technical stakeholders, you will develop AI services involving large language models (LLMs), retrieval-augmented generation (RAG), natural-language-to-SQL generation, and enterprise data integration.

The ideal candidate has strong Python development skills, practical experience deploying generative AI applications, and a solid understanding of AWS cloud infrastructure and secure, scalable software architecture.

This is a hands-on engineering position focused on developing production-ready AI applications within a multi-tenant SaaS and IoT environment.

Key Responsibilities
Generative AI & LLM Development
  • Design, develop, and maintain enterprise-grade generative AI applications and conversational analytics solutions.
  • Build end-to-end conversational AI workflows involving natural-language understanding, contextual retrieval, SQL generation, query validation, and response generation.
  • Integrate commercial and open-source large language models through platforms such as OpenAI, Anthropic, Amazon Bedrock, and Hugging Face.
  • Develop and optimize prompts, model orchestration workflows, and AI response validation mechanisms.
  • Implement multi-turn conversational experiences with contextual memory and reliable conversation-state management.
  • Evaluate AI model performance and improve response accuracy, reliability, and efficiency.
Retrieval-Augmented Generation (RAG) & Data Integration
  • Design and implement RAG pipelines using embeddings, vector databases, and enterprise knowledge sources.
  • Develop contextual retrieval mechanisms that provide accurate, relevant information while maintaining tenant isolation.
  • Integrate vector search technologies such as OpenSearch, FAISS, Pinecone, or ChromaDB.
  • Build natural-language-to-SQL capabilities that translate business questions into validated database queries.
  • Implement safeguards to enforce data-access policies, query restrictions, and enterprise security requirements.
  • Collaborate with data engineering and application development teams to integrate AI capabilities with existing systems.
Python Development & AI Microservices
  • Develop scalable Python-based APIs and AI microservices using FastAPI, Flask, Django, or comparable frameworks.
  • Design and maintain modular, secure, and production-ready AI service architectures.
  • Integrate AI services with existing backend applications, frontend interfaces, and enterprise analytics platforms.
  • Develop automated tests and validation procedures to ensure application quality and reliability.
  • Maintain technical documentation, architecture decision records, and development standards.
  • Deploy, configure, and maintain AI applications and supporting services within AWS environments.
  • Work with AWS technologies such as Amazon Bedrock, OpenSearch, Kendra, Lambda, ECS, EC2, S3, API Gateway, and CloudWatch.
  • Support containerized application deployment using Docker and established CI/CD pipelines.
  • Monitor application performance, infrastructure efficiency, response latency, and operational reliability.
  • Identify and implement improvements to scalability, system availability, and infrastructure utilization.
AI Performance, Security & Continuous Improvement
  • Develop evaluation and monitoring capabilities to measure AI response quality, SQL accuracy, latency, and user feedback.
  • Implement security controls that protect enterprise information and enforce multi-tenant data isolation.
  • Support responsible AI development through appropriate validation, access controls, and data governance practices.
  • Troubleshoot production issues, identify root causes, and implement corrective improvements.
  • Collaborate with engineering teams to deliver intuitive, reliable, and scalable AI-driven analytics experiences.
Required Qualifications
  • 5+ years of overall relevant professional experience, including at least 3 years developing and deploying AI-powered applications, conversational AI solutions, or chatbots.
  • Bachelor's or Master's degree in Computer Science, Data Science, Software Engineering, or a related discipline.
  • Demonstrated experience integrating large language models (LLMs) using OpenAI, Anthropic, Amazon Bedrock, Hugging Face, or comparable platforms.
  • Practical experience developing retrieval-augmented generation (RAG) solutions using embeddings, vector search, and contextual retrieval pipelines.
  • Strong understanding of prompt engineering, model orchestration, AI output validation, and conversational workflows.
  • Hands-on experience with AWS services supporting AI applications, such as Bedrock, Kendra, OpenSearch, ECS, Lambda, and CloudWatch.
  • Working knowledge of SQL, database query validation, enterprise data security, and multi-tenant architectures.
  • Experience with Docker, Git-based CI/CD workflows, and microservice architectures.
  • Strong analytical thinking, problem-solving abilities, and technical communication skills.
  • Ability to collaborate effectively with backend, frontend, data engineering, and product development teams.
Preferred Qualifications
  • Experience hosting, deploying, or fine-tuning open-source language models.
  • Familiarity with AI orchestration frameworks such as LangChain, Haystack, or Semantic Kernel.
  • Experience developing agent-based AI workflows and advanced conversational applications.
  • Experience integrating AI microservices with Angular frontend applications and .NET backend systems.
  • Familiarity with observability and monitoring tools such as OpenTelemetry, Prometheus, or Grafana.
  • Knowledge of enterprise data governance, role-based access controls, AI security, and compliance frameworks.
  • Experience with AI evaluation methodologies, response-quality monitoring, or automated testing frameworks.
  • Contributions to open-source AI projects or experience developing custom LLM integrations.
Technology Environment

The successful candidate will work with technologies commonly used in modern generative AI and enterprise application development.

Experience with comparable technologies is welcome; candidates are not expected to have worked with every tool listed.

Programming Languages & APIs
  • Python 3.10+
  • FastAPI
  • .NET and Python microservices
  • OpenAI
  • Amazon Bedrock
  • LangChain
  • Haystack
  • Semantic Kernel
Vector Search & Data Retrieval
  • Amazon OpenSearch
  • FAISS
  • Pinecone
  • ChromaDB
  • Amazon Bedrock
  • AWS Lambda
  • Amazon ECS and EC2
  • Amazon S3
  • API Gateway
  • Amazon CloudWatch
Application Development & DevOps
  • Docker
  • GitHub Actions
  • AWS CDK
  • Redis or DynamoDB
  • OpenTelemetry
Frontend & Data Visualization
  • Angular
  • Chart.js
  • D3.js
What We're Looking For

We are seeking a technically strong, hands-on engineer who enjoys building practical AI solutions that solve real business problems.

The successful candidate should be comfortable developing production-ready generative AI applications, working with enterprise data, and integrating AI capabilities into existing software platforms.

You should have a strong understanding of how to balance AI innovation with security, reliability, scalability, and performance.

We value individuals who take ownership of their work, collaborate effectively across technical teams, and continuously look for opportunities to improve the quality and effectiveness of the solutions they develop.

What Success Looks Like
  • Deliver reliable conversational AI solutions that transform natural-language business questions into accurate, actionable insights.
  • Develop secure and scalable RAG pipelines and AI microservices that integrate with enterprise applications.
  • Ensure generated SQL queries are validated and comply with established data-access policies.
  • Maintain strict tenant isolation and appropriate enterprise security controls.
  • Improve AI response accuracy, application performance, reliability, and user experience.
  • Deliver measurable improvements in AI-driven analytics and operational decision-making.
Why Join IRISS?

At IRISS, you'll have the opportunity to contribute to innovative technologies that improve industrial safety, equipment reliability, and operational performance worldwide.

You’ll work with modern generative AI technologies and collaborate with engineering teams developing intelligent, connected solutions for industrial environments.

Your contributions will help shape the future of conversational analytics and AI-powered insights within our growing SaaS and IoT technology ecosystem.

We offer a collaborative, innovation-driven environment where technical expertise, problem-solving, and continuous improvement are valued.

Join IRISS and help us advance our mission: We Humanize Safety.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

GEN AI - Graduate Engineer
GEN AI - Graduate Engineer

Iris Software • Dadri

On-site
INR 2,800,000 - 4,200,000
AI Engineer's - Pune, India
AI Engineer's - Pune, India

EIRIS • Pune District

On-site
INR 1,200,000 - 2,000,000
AI Solutions - Senior Engineer
AI Solutions - Senior Engineer

Mployee.me • India

On-site
INR 4,000,000 - 7,000,000
AI Solutions - Senior Engineer
AI Solutions - Senior Engineer

Iris Software Inc. • Dadri

On-site
INR 1,500,000 - 3,000,000
Senior AI Platform Software Engineer
Senior AI Platform Software Engineer

Spore N Sprouts • Hyderabad

On-site
INR 1,800,000 - 3,000,000
AI Ops - Senior Engineer
AI Ops - Senior Engineer

Iris Software, Inc. • Dadri

On-site
INR 2,800,000 - 4,000,000
AI Solutions - Senior Engineer
AI Solutions - Senior Engineer

Iris Software • Dadri

On-site
INR 2,500,000 - 4,000,000
Azure AI Platform - Senior Engineer
Azure AI Platform - Senior Engineer

Iris Software, Inc. • Dadri

On-site
INR 1,200,000 - 2,100,000
Click here to view benefits
AI/ML Engineer
AI/ML Engineer

ISHIR • India

Remote
INR 1,200,000 - 1,800,000
Senior AI Engineer
Senior AI Engineer

Phenom Cloud • NTR

On-site
INR 2,500,000 - 6,000,000
Work on cutting-edge Generative AI
Exposure to global clients
Continuous learning
+2