Lead Backend Engineer

Your responsibilities will include designing and implementing scalable backend services and APIs using Node.js and modern frameworks such as Express and NestJS. You will lead the architecture and integration of LLMs (OpenAI, Anthropic, open-source models) into production applications, focusing on prompt engineering to fine-tune LLM outputs for specific business tasks. Additionally, you will be responsible for building and optimizing chatbot platforms and conversational AI pipelines. Collaboration with AI/ML engineers, frontend developers, product managers, and designers to deliver robust AI-driven features is a key aspect of this role. You will guide and mentor a team of engineers through best practices in backend engineering, code quality, and system design. Implementing observability, performance tuning, and API reliability measures will also be part of your responsibilities. Staying up to date with advancements in GenAI, NLP, and emerging LLM capabilities is essential.

To be successful in this role, you should have 7-10 years of backend development experience with a strong foundation in Node.js. Proven experience in building and deploying applications using LLMs and Generative AI (OpenAI, Claude, Llama, etc.) is required. A solid understanding of Prompt Engineering, prompt tuning, and context management for LLMs is crucial. Experience with chatbot frameworks such as Dialogflow, Rasa, Botpress, or custom solutions is necessary. Strong knowledge of RESTful APIs, WebSockets, and asynchronous programming is expected. Familiarity with vector databases (Pinecone, Weaviate, FAISS) and retrieval-augmented generation (RAG) is a plus. Proficiency in working with cloud platforms (AWS/GCP/Azure), a strong understanding of system design, architecture patterns, and scalability principles, as well as excellent problem-solving, communication, and leadership skills are important for this role.,