Shamanth Keni
Deep Agents | GenAI Dev | Python | Javascript | Langchain Framework @NTT Data - Innovative Centre
Bengaluru
3+ years of work experience
Nov 202511 mosPresent
Bengaluru, Karnataka, India
•Deep Agentic SDLC Platform: Architected an enterprise-grade multi-agent "Swarm" using LangGraph and Hierarchical Task DAGs (HTDAG), delegating complex software lifecycles to isolated subagent workers (PMO, Coder, Tester) to achieve strict context isolation and parallelized execution.
•Self-Correction & Trajectory Evaluation: Engineered recursive, two-stage planner-executor self-correction loops enabling "Tester Agents" to run unit-test diagnostics and trigger iterative code refactoring in "Coder Agents"; used AgentFence trace-auditing benchmarks to eliminate wrong-principal and unauthorized tool-use actions.
•MCP-Based Tool Connectivity: Designed and deployed Model Context Protocol (MCP) servers that exposed developer environments (GitHub, Jira, CI/CD pipelines) as standardized tools to frontier LLMs, streamlining manual workflow handoffs into conversational, natural-language automation.
•Enterprise Leadership & Demonstration: Spearheaded live system demonstrations at the APAC Horizons Innovation Summit, showcasing measurable AI-driven business transformations including a 65% reduction in manual pipeline failures and accelerated code delivery.
May 20241 yr 7 mosNov 2025
Bangalore Urban, Karnataka, India
•Built AI agents and enterprise chatbots using OpenAI GPT-4o-Mini, LangChain, and LangGraph to automate complex business queries.
•Improved response accuracy via vector DB integration and prompt engineering.
•Unified observability data into conversational interfaces for incident classification and ML-based auto-remediation.
•Integrated tools like ServiceNow, Jira, and Dynatrace to streamline incident management.
•Received “Techie of the Quarter” award for impactful AI agent development and enterprise chatbot solutions.
Nov 20237 mosMay 2024
Bengaluru, Karnataka, India
• Led the frontend design of Skill Matrix, an internal
application, using React.js and Material-UI, enabling
employees to update their skills and managers to
validate them in a hierarchical structure.
• Developed an admin page for monitoring the entire
system and implemented functions for selecting skills
(domain, sub-domain, and skill) with logic written
using both top-down and bottom-up approaches.
Nov 20237 mosMay 2024
•Led frontend development of Skill Matrix using React.js and Material-UI for hierarchical skill validation.
•Built an admin dashboard and implemented skill selection logic using top-down and bottom-up approaches.
Aug 202210 mosMay 2023
Bengaluru, Karnataka, India
ML-based Purchase Analytics Project: Developed
and implemented machine learning models to analyze
large volumes of purchasing data, identifying trends,
patterns, and anomalies. Created predictive models to
forecast demand, optimize procurement strategies,
and reduce inventory costs. Improved decision-
making by presenting actionable insights through
visual dashboards, enabling better strategic planning
and operational efficiency.
Shamanth’s AI Stack
Education
Bachelor of Engineering - BE, Electronics and Communication engineering
BNM Institute of Technology
20194 yrs2023
Join Shamanth and 10k+ other professionals on
Tal is the app where bosses meet engineers & builders directly, without middlemen
Download Tal Boss