Join Iris Software, a rapidly growing IT services company recognized as one of India's Top 25 Best Workplaces in the IT industry. We seek talented professionals to realize their full potential within an award-winning culture that values ambition and talent. With a global presence and over 4,300 associates, we empower enterprise clients across financial services, healthcare, transportation & logistics, and professional services through technology-enabled transformation, focusing on complex, mission-critical applications.

At Iris, we believe in empowering our employees with ownership of their career journeys. Our "Build Your Future. Own Your Journey." philosophy fosters a culture of growth, impact, and continuous learning. Experience cutting-edge projects, personalized development, and mentorship that supports your professional and personal evolution.

Lead the end-to-end design and development of Generative AI-powered applications, translating customer requirements into scalable AI architectures and leveraging cloud services. Drive the adoption of LLM orchestration frameworks like LangChain and LangGraph, while staying abreast of Gen AI advancements and initiating Proofs of Concept for novel solutions.

Develop robust RAG pipelines using vector databases and embeddings, design and implement agentic workflows, and optimize vector search capabilities with tools like PGVector and FAISS. Create efficient embedding pipelines, manage chunking strategies, apply metadata tagging, and refine retrieval processes.

Build backend services, API layers, and model-serving components using Python (Flask), ensuring performance and security are paramount. Utilize AWS services such as ECS, API Gateway, S3, Bedrock, CloudWatch, and SageMaker effectively.

Mentor a team of engineers, conduct code and design reviews, and collaborate closely with Product, Architecture, Security, and Data Engineering teams. Champion best practices in coding, testing, observability, and DevOps.

A seasoned Lead Engineer with 8-10 years of experience is needed, possessing strong expertise in Python, AWS Cloud, and Generative AI. Proven hands-on experience with RAG (Retrieval Augmented Generation), agentic workflows, and building LLM-powered applications is essential.

Key technical proficiencies include deep knowledge of Python (Flask, REST, async programming) and extensive experience with Generative AI concepts, LLM applications, RAG development, embeddings, and vector databases. Familiarity with agent frameworks like LangChain, LangGraph, or custom agents is required.

A solid understanding of cloud architectures (AWS/Azure/GCP), API development, microservices, and event-driven systems is necessary. Experience with CI/CD pipelines, Docker, and Git integration tools (GitLab/GitHub Actions) is also expected. Familiarity with AWS services such as ECS, API Gateway, S3, Bedrock, CloudWatch, and SageMaker is mandatory.