Role: Senior Backend Developer (MERN Stack — AI-First)
Experience: 5+ Years
Location: Gurugram
Role Summary
As a Senior Backend Engineer, you will design and implement robust, scalable, high-performance backend services while working in an AI-first, agentic engineering culture. You will contribute to architectural decisions, solve complex technical problems, and mentor engineers across the stack, with a strong emphasis on Node.js, Express.js, MongoDB, and backend architecture. Beyond building services, you will design and ship AI-powered product features (LLM-backed APIs, retrieval pipelines, agentic workflows) and use AI coding agents hands-on to accelerate your own delivery. Familiarity with Docker and CI/CD pipelines is a plus.
Key Responsibilities
- Architect and implement backend services and REST APIs using Node.js and Express.js.
- Design scalable data models and work with MongoDB and NoSQL databases efficiently.
- Design and ship AI-powered product features — integrate LLM APIs, build retrieval-augmented (RAG) pipelines, and expose model-backed capabilities through clean, well-governed backend services.
- Build and operate agentic workflows — tool-using agents, function/tool calling, orchestration, guardrails, evaluations, and human-in-the-loop checkpoints for production reliability.
- Work AI-first, hands-on — use AI coding agents (e.g. Claude Code, Cursor, Copilot) daily to design, write, review, and refactor code, and help set the team's standards for effective, safe AI-assisted development.
- Solve complex problems related to performance, scalability, and data integrity.
- Ensure code quality through test coverage, peer reviews, and automated workflows — including evals and regression checks for AI/LLM features (accuracy, latency, cost, and safety).
- Manage background jobs, queues, and event-driven architecture, including asynchronous and long-running AI/agent jobs.
- Collaborate with frontend developers, product managers, and DevOps for feature implementation.
- Lead the technical architecture of new features and services, including the AI/agent layer and its integration with core systems.
- Ensure application security and data protection protocols, including responsible-AI practices — prompt-injection defense, PII handling, data residency (DPDP), and cost/rate controls on model usage.
- Optimize applications for performance, scalability, and maintainability.
- Mentor and guide junior engineers, ensuring best coding practices — and AI-assisted engineering practices — are followed.
- Participate in sprint planning, technical discussions, and release management.
Qualifications
- Education: B.Tech in Computer Science, Information Technology, or related field.
- 5+ years of hands-on experience with the MERN stack, especially in backend development.
- Proficiency in JavaScript and Node.js, with deep understanding of Express.js.
- Strong database knowledge, especially MongoDB, including schema design and optimization.
- Hands-on experience building with LLMs — integrating model APIs (OpenAI, Anthropic, or similar), prompt design, structured outputs / tool calling, and shipping at least one AI feature to production or a serious prototype.
- Practical, day-to-day use of AI coding agents (Claude Code, Cursor, Copilot, or equivalent) as part of your development workflow.
- Experience architecting scalable backend systems.
- Familiarity with Docker, containerization concepts, and CI/CD pipelines (e.g., GitHub Actions, Jenkins.)
- Understanding of REST APIs, microservices, and API documentation (Swagger/OpenAPI).
- Familiarity with Redis and message queues (RabbitMQ, Kafka) is a plus.
- Strong problem-solving and analytical skills.
- Excellent written and verbal communication.
Good to Have
- Experience with agent frameworks and orchestration (LangChain, LangGraph, LlamaIndex, or the Vercel AI SDK) and with the Model Context Protocol (MCP).
- Vector databases and retrieval (pgvector, Pinecone, Weaviate, MongoDB Atlas Vector Search) and embedding-based search.
- LLM evaluation and observability — eval harnesses, tracing, and monitoring model cost, latency, and quality in production.
- Exposure to cloud platforms like AWS (EC2, S3, Lambda, Bedrock).
- Experience with monitoring/logging tools (ELK Stack, Prometheus, Grafana).
- Knowledge of GraphQL, WebSockets, or gRPC.
- Fine-tuning, RAG optimization, or self-hosted / open-weight model experience.
- Contribution to open-source or public code repositories.