Shulabh
AI/ML Engineer
Hire this person
Send a job offer directly to this candidate
About
AI/ML Engineer with 2+ years of experience designing, developing, and deploying intelligent applications using Machine Learning, Generative AI, and Large Language Models (LLMs). Skilled in developing LLM-based applications, Retrieval-Augmented Generation (RAG) pipelines, prompt engineering frameworks, and scalable AI microservices. Proven ability to deliver enterprise AI solutions, workflow automation, and intelligent assistants deployed on cloud platforms like AWS and Azure.
Experience
AI Engineer / Generative AI Engineer - Scale AI - San Francisco, CA
(2026-01)
- Implemented Retrieval-Augmented Generation (RAG) pipelines integrating vector databases such as Pinecone and FAISS for enhanced contextual AI responses.
- Engineered advanced prompt engineering frameworks to improve reasoning, response accuracy, and reduce hallucinations in LLM outputs.
- Built intelligent AI assistants and chatbot systems for customer support automation and internal productivity tools.
- Collaborated with product and engineering teams to design AI-powered SaaS products and AI automation workflows.
- Developed scalable LLM-powered applications for document intelligence, semantic search, and contextual question-answering systems.
- Built advanced Retrieval-Augmented Generation (RAG) pipelines integrating vector databases and embedding models to improve response accuracy.
- Engineered AI agent frameworks capable of performing multi-step reasoning and automated task execution across enterprise tools.
- Designed optimized prompt engineering strategies and evaluation pipelines to improve model reliability and reduce hallucinations.
- Implemented real-time AI workflow automation systems to support operational decision-making and data-driven insights.
- Built intelligent AI copilots and conversational assistants to support internal teams with automated analytics and reporting.
- Collaborated with product managers and engineering teams to design AI-powered SaaS capabilities for enterprise customers.
AI Engineering Intern - Neuroscience Department | DePauw University - Greencastle, IN
(2024-08 - 2025-12)
- Implemented semantic search systems and embedding pipelines using vector databases to power enterprise knowledge retrieval solutions.
- Designed scalable AI backend services using Python, Fast API, and containerized deployments with Docker.
- Integrated AI capabilities into enterprise products through REST APIs and AI integration layers.
- Collaborated with product teams to deliver AI-driven features for SaaS platforms and enterprise tools.
- Integrated Large Language Model APIs into enterprise platforms to deliver intelligent features within existing products.
- Constructed prompt templates and prompt optimization techniques to improve model output consistency and contextual understanding.
- Created data preprocessing and document indexing pipelines to support efficient LLM-based search and analytics workflows.
- Conducted testing and evaluation of LLM outputs and model performance to ensure reliability in production environments.
- Assisted in optimizing AI pipelines to improve system performance, scalability, and response latency.
Education
B.A. - Computer Science - DePauw University
