We are looking for a skilled AI Senior Software Engineer to design and build Generative AI applications that solve real business problems. This is a Gen AI–first role: your primary work will be developing LLM-powered systems using frameworks like LangChain, LangGraph, and Hugging Face, with RAG pipelines, vector search, and prompt engineering at the core of what you do.
Our architecture separates AI services from the user-facing application. Your primary focus is owning the AI services end-to-end — from model integration and inference pipelines through to production deployment. This split lets you go deep on AI while still maintaining visibility into how your work ships to customers.
You will collaborate with product managers, engineers, and business stakeholders to deliver AI features that create measurable value.
• 3–8 years of professional software development experience, with at least 1–2 years focused on Generative AI or LLM application development.
• Hands-on production experience building LLM-powered applications using LangChain and/or LangGraph.
• Practical experience with Hugging Face — using pre-trained models, the Transformers library, or the Inference API.
• Working knowledge of RAG architectures, vector databases (e.g. Pinecone, Weaviate, pgvector, or MongoDB Atlas Vector Search), and embedding techniques.
• Robust Python skills — writing clean, well-tested, and maintainable code, ideally with experience in FastAPI or similar API frameworks.
• Working proficiency in the MEAN stack: MongoDB, Express.js, Angular (17+), and Node.js.
• Experience designing and consuming REST APIs; familiarity with GraphQL is expected for this role.
• Comfortable using Git and working within modern CI/CD workflows.
• Clear communicator who works effectively with both technical and non-technical stakeholders.
Nice to Have
• Experience deploying AI-powered applications on any one of the cloud providers: AWS, Azure, or GCP.
• Exposure to LLM evaluation frameworks, observabili
📌 Senior Software Engineer (India)
🏢 MCO
📍 India