Advance your career at Iris Software, recognized among India's Top Workplaces in IT. Join a dynamic, award-winning culture that fosters talent and ambition. As a leading IT services company, we empower our clients across financial services, healthcare, and transportation with cutting-edge technology solutions.

Our vision is to be the premier technology partner for enterprises, leveraging expertise in Application & Product Engineering, Data & Analytics, Cloud, DevOps, and MLOps. We believe in providing a launchpad for your professional growth, where you own your journey and shape your success.

Discover a workplace that values your potential, amplifies your voice, and enables you to make a real impact. With exciting projects, tailored career development, and robust mentorship, Iris supports your holistic growth.

Design and develop advanced Generative AI and LLM-based applications using Python. Build and implement sophisticated Retrieval-Augmented Generation (RAG) pipelines tailored for enterprise needs. Create dynamic AI workflows and agentic applications utilizing LangChain and LangGraph frameworks.

Implement robust vector search and semantic retrieval capabilities with PostgreSQL and PGVector. Work extensively with LLMs, embeddings, prompt engineering, document processing, and context retrieval mechanisms. Develop scalable, production-ready AI services and APIs.

Deploy and seamlessly integrate AI applications with AWS cloud services. Optimize RAG pipelines for enhanced accuracy, relevance, reduced latency, and scalability. Collaborate closely with product, engineering, and data teams to translate business requirements into innovative AI solutions. Ensure code quality through clean, maintainable, testable, and well-documented practices. Proactively troubleshoot performance, integration, and production issues within AI applications.

A minimum of 5 years of comprehensive software development experience is essential. Demonstrate strong hands-on proficiency in Python, alongside extensive experience with PostgreSQL and PGVector for vector database implementation.

Possess a deep understanding and practical experience in building Retrieval-Augmented Generation (RAG) systems. Showcase hands-on expertise with LangChain and LangGraph for developing AI workflows and agentic applications. Solid experience in deploying and managing applications on AWS cloud infrastructure is required.

Familiarity with LLMs, embeddings, vector search concepts, prompt engineering techniques, and overall AI application architecture is crucial. The ideal candidate is a practical, hands-on engineer with a proven track record in building and deploying production-grade GenAI applications.