Shantanu Sharma

I am an AI/ML Engineer with 3+ years of experience designing and building production-grade Generative AI applications, scalable backend systems, and event-driven SaaS platforms. I have led a 12-member cross-functional engineering team, driving technical architecture, code reviews, technology selection, and end-to-end product delivery. My expertise includes Python, FastAPI, Go, LangChain, Retrieval-Augmented Generation (RAG), vector databases, prompt engineering, LLM integration, and cloud-native backend development. I have built production AI solutions such as RAG-based knowledge systems, natural language search over structured data, NLP-powered recommendation engines, and AI interview platforms using AWS services including Chime, EventBridge, SQS, RDS, EC2, and S3. I also have experience developing high-throughput distributed systems using RabbitMQ, Docker, Redis, PostgreSQL, MongoDB, and REST APIs. Beyond AI, I enjoy solving complex software engineering challenges by designing scalable, reliable, and maintainable systems. I have worked across backend, frontend, and mobile products while collaborating with distributed teams and delivering features used by businesses in production. I am currently seeking full-time remote opportunities where I can contribute to building innovative AI products, LLM-powered applications, intelligent automation platforms, and scalable backend infrastructure. I work comfortably with globally distributed teams, communicate effectively in English, and can provide meaningful overlap with US and European business hours.