
1
1
India
1 year of experience
Software Engineer at HCLTech with 1+ year of experience in enterprise application management, backend systems, and automation engineering. Skilled in maintaining production-grade systems, monitoring multi-service architectures, optimizing SQL databases, and resolving critical incidents to ensure system reliability. Successfully improved operational efficiency by reducing manual engineering effort by ~30% through Python-based automation and process optimization. Passionate about transitioning into AI engineering, with hands-on experience building Generative AI applications and intelligent systems. Developed and deployed an AI Text Summarizer Agent using Gemini 2.5 Flash, leveraging Google ADK, Docker, and Google Cloud Run as part of the Google Gen AI APAC 2026 Competition. Also built an AI-driven content automation pipeline, reducing manual content creation effort by over 60%. Proficient in Python, SQL, Bash, and JavaScript, with working knowledge of LangChain, AI agents, prompt engineering, Dialogflow, and Gemini APIs. Experienced with GCP services including Cloud Run and BigQuery, along with DevOps tools like Docker, Kubernetes, and Ansible. Certified across Google, Microsoft, NVIDIA, and Red Hat with 35+ verified credentials. Currently pursuing a BCA from Amity University Online while working full-time, and actively seeking opportunities to build scalable, real-world AI solutions.

AMD DevAssist is a multi-agent AI system that eliminates setup friction for AMD Developer Cloud users. A user describes their development goal in plain English. Three specialized LangChain agents — a Search Agent, a Code Generation Agent, and a Review Agent — collaborate to produce accurate, ROCm-compatible setup guides and working code in seconds. Built with: LangChain.js, Llama 3.1 70B, Groq inference, Next.js 14, Tailwind CSS, deployed on Vercel. Designed for production deployment on AMD Instinct MI300X via vLLM. This directly addresses the real friction point in AMD developer adoption — making AMD's powerful compute stack accessible to every developer, not just GPU experts.
10 May 2026