Job
Description
About the Role We are looking for a Senior Backend Engineer with expertise in scalable backend systems and Large Language Models (LLMs). You will play a key role in architecting, developing, and optimizing AI-driven workflows while mentoring junior engineers and driving technical excellence. This role involves working with Retrieval-Augmented Generation (RAG) systems, agentic workflows, and vector databases to power LLM-backed applications. You will be responsible for designing efficient REST APIs, managing SQL & NoSQL databases, and ensuring seamless scalability of AI-driven backend services. Key Responsibilities Architect & develop scalable backend systems for AI applications. Implement LLM workflows, including tool calling, RAG pipelines, and agentic processing. Optimize vector databases for efficient retrieval & similarity search. Build & optimize REST APIs with FastAPI or similar frameworks. Ensure high-performance database management with PostgreSQL, SQLite, or SQL Server. Implement caching & optimization strategies for LLM-driven inference. Work with DevOps & deployment best practices to enhance system reliability. Mentor & guide junior engineers on best practices & AI backend workflows. Maintain code quality, documentation, and system security best practices. Required Skills and Experience Programming: Expert-level proficiency in Python. Backend Development: Strong experience with FastAPI, Flask, or Django. LLM Workflows: Experience in RAG, vector search, embeddings, tool calling, and agentic workflows. Database Management: Deep knowledge of SQL & NoSQL databases (PostgreSQL, SQL Server, SQLite, Redis, or MongoDB). Scaling & Optimization: Proven experience optimizing backend performance & AI inference workloads. Version Control: Expertise in Git & CI/CD workflows. Cloud & Deployment: Familiarity with Docker, Kubernetes, and cloud services (AWS/GCP/Azure). Leadership & Mentorship: Ability to mentor junior engineers & drive technical decisions. Preferred Skills Experience with LangChain or similar AI frameworks. Knowledge of retrieval-based search optimization (FAISS, Pinecone, Weaviate, ChromaDB, etc.). Exposure to LLM fine-tuning or prompt engineering. Basic knowledge of frontend integration (JavaScript, Vue.js, React, or similar frameworks). Work Environment Hybrid role (Work from Office in Mangalore/Bangalore, with remote flexibility). Work hours must overlap with US time zones. Collaborative & innovation-driven environment with a focus on AI & automation. Qualifications Bachelors or Master’s degree in Computer Science, Software Engineering, or related fields. 5+ years of professional experience in backend development with AI-driven applications. What We Offer Competitive salary & performance-based incentives. Opportunities to work on cutting-edge AI & LLM applications. Hybrid work flexibility while maintaining team collaboration. Career growth opportunities in AI and backend engineering.
