Join Iris Software, a rapidly expanding IT services firm recognized among India's Top 25 Best Workplaces in the IT industry. We offer an award-winning culture that champions your talent and ambitions, providing a platform to truly own and shape your career journey. As a trusted technology partner for enterprise clients across diverse sectors, we specialize in complex, mission-critical applications leveraging cutting-edge technologies like Data & Analytics, Cloud, DevOps, and AI.

At Iris, every role is designed as a launchpad for significant professional growth. Our philosophy, 'Build Your Future. Own Your Journey.,' underscores our commitment to empowering individuals with career ownership and opportunities for development. Experience a culture that values your potential, amplifies your voice, and ensures your work creates tangible impact. Through advanced projects, tailored career development, continuous learning, and mentorship, we are dedicated to fostering your personal and professional excellence.

Lead the end-to-end design and development of Generative AI-powered applications, translating customer needs into scalable AI architectures using cloud services. Drive the adoption of LLM orchestration frameworks such as LangChain and LangGraph, while actively exploring and prototyping emerging Gen AI solutions.

Develop robust RAG pipelines using vector databases, embeddings, and document indexing, implementing efficient vector search with tools like PGVector or FAISS. Design and implement agentic workflows, creating optimized embedding pipelines, chunking strategies, metadata tagging, and retrieval mechanisms.

Build scalable backend services, API layers, and model-serving components using Python (Flask), integrating with key AWS services like ECS, API Gateway, S3, Bedrock, CloudWatch, and SageMaker, prioritizing performance and security.

Mentor a team of engineers, conduct thorough code and design reviews, and collaborate closely with cross-functional teams including Product, Architecture, and Security. Ensure adherence to best practices in coding, testing, observability, and DevOps.

We are seeking an experienced Lead Engineer with 8-10 years of experience, possessing deep expertise in Python, AWS Cloud, and Generative AI. Proven hands-on experience with Retrieval Augmented Generation (RAG), agentic workflows, and building LLM-powered applications is essential.

Required skills include strong proficiency in Python (Flask, REST, async programming), deep knowledge of Generative AI and LLM applications, and expertise in RAG development, embeddings, and vector databases. Experience with agent frameworks (LangChain, LangGraph, ReAct, OpenAI Assistants, or custom agents) and a strong understanding of cloud architectures (AWS/Azure/GCP) are also critical. Familiarity with API development, microservices, event-driven systems, CI/CD pipelines, Docker, and GitLab/GitHub Actions is expected.