Sde Ii

SDE II – Backend Engineer (AI Platforms) Stealth AI Startup Location: Hyderabad / Bangalore Work Model: Hybrid Experience: 3–6 Years Employment Type: Full-time About the Role We are a well-funded Stealth AI Startup building enterprise-grade AI platforms that power Retrieval-Augmented Generation (RAG) applications and AI Agentic systems across industries such as BFSI, Healthcare, Manufacturing, Retail, and SaaS. As an SDE II – Backend Engineer, you will design and build the backend systems that enable LLM-powered workflows, intelligent agents, and large-scale knowledge retrieval for real-world enterprise use cases. This role sits at the intersection of backend engineering, AI infrastructure, and platform scalability. Key Responsibilities - Design and build backend services for RAG-based applications, including document ingestion, chunking, indexing, retrieval, and response orchestration - Develop backend platforms to support AI Agentic workflows (tool calling, memory, planning, and execution layers) - Build and maintain scalable APIs that integrate LLMs, vector databases, and enterprise data sources - Collaborate with AI/ML teams to productionize LLM pipelines and agent frameworks - Architect high-throughput, low-latency systems for AI inference and retrieval workloads - Own backend components end-to-end: design, development, testing, deployment, monitoring - Ensure enterprise-grade security, observability, and reliability - Participate in architecture reviews, system design discussions, and code reviews Required Qualifications - 3–6 years of experience as a Backend Engineer / Software Engineer - Strong proficiency in Python, Java, Go, or Node.Js (Python preferred) - Hands-on experience building REST / gRPC APIs - Solid understanding of distributed systems and system design - Experience with databases: PostgreSQL/MySQL, Redis, MongoDB - Experience deploying services on AWS, GCP, or Azure - Hands-on experience with Docker; working knowledge of Kubernetes - Strong problem-solving ability and ownership mindset Strongly Preferred / Nice to Have - Hands-on experience with RAG pipelines and LLM-based applications - Experience with vector databases (Pinecone, Weaviate, Milvus, FAISS, OpenSearch, pgvector) - Familiarity with LLM frameworks (LangChain, LlamaIndex, Haystack, CrewAI, AutoGen, Semantic Kernel) - Experience building or integrating AI Agentic platforms (multi-agent systems, tool orchestration, memory layers) - Exposure to event-driven architectures (Kafka, Pub/Sub, RabbitMQ) - Experience with workflow orchestration (Airflow, Temporal, Step Functions) - Knowledge of enterprise security & compliance considerations What You’ll Build - Enterprise RAG platforms serving millions of documents - Agentic AI systems capable of reasoning, planning, and executing multi-step workflows - Backend systems that bridge LLMs, enterprise data, and real-world actions What We Offer - Work on cutting-edge AI platform engineering, not just demos - Opportunity to build from scratch with no legacy constraints - Competitive compensation and equity - High ownership, fast execution, and strong technical culture - Hybrid work model (Hyderabad / Bangalore) Why Join Us - Build AI systems that enterprises actually deploy at scale - Collaborate with senior engineers and AI researchers - Shape the foundation of a next-generation AI platform