PRIYANSH SINGH — Software Engineer
As a Generative AI Engineer and backend systems developer, I specialize in building scalable LLM applications that bridge cutting-edge AI research and enterprise needs. I currently lead the development of an internal chatbot builder platform, empowering non-technical teams to deploy domain-specific assistants using OpenAI, Hugging Face, and custom RAG stacks. My work spans AutoGen-based multi-agent orchestration, LightRAG architectures, and end-to-end pipelines with vector stores and knowledge graphs—covering everything from prompt design and retrieval logic to ingestion flows and agent memory systems. I’ve also developed modular MCP agents for internal tools like Mem0, DevOps OpsCenter, and VSCode Assistant to drive automation and personalization across platforms. My core stack includes Python, FastAPI, Node.js, LangChain, LangGraph, Hugging Face Transformers, and OpenAI APIs. On the infrastructure side, I work with Docker, Kubernetes (AKS), GitHub Actions, and Azure. I’ve built event-driven ingestion pipelines using Ray and CDC syncing with FAISS and Milvus, while leveraging Neo4j for semantic graphs. With a systems-first mindset, I focus on designing low-latency, context-aware LLM responses—whether through modular backends, caching strategies, or scalable deployment workflows. I’m particularly interested in multi-agent control systems (MCP/A2A), efficient retrieval, and long-term memory in LLM applications. I hold a B.Tech in Electronics and Communication Engineering from IIIT Allahabad, which gave me a strong grounding in systems thinking, algorithms, and applied ML. My journey in AI has been hands-on and production-oriented—focused on building usable systems rather than demos, with emphasis on performance, reliability, and user value. Beyond work, I enjoy building full-stack systems that combine backend engineering with applied AI—especially in finance, real-time data, and secure digital platforms. My projects often center on LLM-driven decision support, system auditability, and user personalization through thoughtful architecture. I’m also passionate about decentralized apps, smart auth flows, and leveraging APIs for flexible data interoperability. Recognized as the Best Open Source Contributor in Geekoberfest 2021, I believe in community-driven growth and continuously seek to expand my impact and technical depth. I’m always open to connecting with others working on real-world GenAI systems, retrieval infrastructure, or agentic intelligence.
Stackforce AI infers this person is a SaaS-focused Generative AI Engineer with expertise in scalable backend systems.
Location: Bengaluru, Karnataka, India
Experience: 2 yrs 11 mos
Skills
- Generative Ai
- Large Language Models (llm)
- Vector Databases
Career Highlights
- Expert in building scalable LLM applications
- Led development of internal chatbot builder platform
- Recognized as Best Open Source Contributor in Geekoberfest 2021
Work Experience
Jio Platforms Limited (JPL)
Generative AI Engineer (2 yrs 11 mos)
Education
Bachelor of Technology - BTech at Indian Institute Of Information Technology Allahabad