Suddapalli Gangadhar
Software Developer at Accelnomics Technologies
Andhra Pradesh
2+ years of work experience
Mar 20242 yrs 7 mosPresent
Bengaluru
• Architected an AI Agent Platform that automates Tier-1 technical support workflows, reducing average response time by 50% and freeing the support team to focus on complex escalations.
• Built a RAG pipeline on QDrant vector database with hybrid semantic and keyword retrieval, indexing the company knowledge base to deliver grounded, context-aware answers and cut hallucinations. • Designed an LLM evaluation framework covering hallucination, retrieval relevance, and tone, gating each production deploy on regression-test pass rates against a curated test set of real support tickets.
• Engineered multi-step agent workflows with LangChain and OpenAI, including tool use, conversation memory, and fallback handling for ambiguous or out-of-scope queries.
• Iterated on prompt strategies (few-shot, chain-of-thought, structured JSON output) to lift accuracy on edge-case tickets and standardize agent responses. • Owned full-stack delivery across a polyglot architecture: React.js front end, Node.js + Express.js backend services, and FastAPI (Python) services for AI/LLM workloads, with MongoDB persistence and CI/CD deploys on Azure.
Jan 20234 mosApr 2023
India
Suddapalli’s AI Stack
Education
Bachelor of Technology - BTech, Computer Science
Lovely Professional University
20194 yrs2023
Intermediate, MPC
Nri junior college
20172 yrs2019
Join Suddapalli and 10k+ other professionals on
Tal is the app where bosses meet engineers & builders directly, without middlemen
Download Tal Boss