Software Engineer

About the Role We are looking for a Senior Software Engineer with full-stack developer with strong Java expertise and hands-on experience in building Retrieval-Augmented Generation (RAG) systems. You will design, develop, and deploy AI-powered applications on cloud-native infrastructure, working closely with cross-functional teams to deliver scalable, production-grade solutions. Must-Have Requirements Designed and implemented RAG pipelines end-to-end (document ingestion, chunking, embedding, vector storage, retrieval, and generation) Experience with vector databases (e.g., Pinecone, Weaviate, pgvector, OpenSearch) and familiarity with LLM orchestration frameworks (LangChain, LlamaIndex, or similar) POC-level experience is acceptable if depth of work is demonstrable. Strong proficiency in core Java and Spring Boot / Spring Cloud Building RESTful APIs and microservices at scale Designing and operating event-driven architectures, Familiarity with Kafka Connect or Kafka Streams is a plus, Deploying and managing containerized workloads on Amazon EKS Writing and maintaining Helm charts for Kubernetes deployments Working knowledge of EC2 instance management, networking, and IAM Experience with NoSQL databases such as MongoDB Or Amazon DocumentDB and caching solutions like Redis. Familiarity with CI/CD tools like Harness and monitoring/logging platforms like Splunk. What You'll Do Architect and build RAG-based features that integrate LLMs into existing product workflows Develop high-throughput Java microservices backed by Kafka event streams Package, deploy, and operate services on AWS EKS using Helm Collaborate with data, platform, and product teams to define technical direction Mentor junior engineers and contribute to engineering standards Qualifications B.Tech / B.E. / M.Tech in Computer Science or equivalent experience 5–7 years of professional software engineering experience Strong communication skills and ability to work in an Agile environment Self-driven with a bias for action and ownership