FortyGuard
Software Development Engineer Intern
July 2026–Present
Agent backends using LangGraph, MCP server/tool integrations using FastMCP, streaming responses, and dashboard integration.
Explore my work at FortyGuardAbout
Rohit Kshirsagar
I’m Rohit, a software engineer focused on backend systems and applied AI. I work on agents and MCP integrations at FortyGuard, and previously built asynchronous AI/media workflows at Tessact. My personal projects explore systems programming, networking, and educational software.
Experience
Tessact
Software Engineer Intern
February–May 2026 · Bengaluru
A seven-stage asynchronous AI and media-processing pipeline, with job tracking and failure recovery.
Explore my work at TessactApexAI Solutions Pvt Ltd
AI Engineer Intern
June–September 2025
Multilingual NLP workflows for Hinglish transcript classification and LLM-assisted transcript-to-JSON conversion.
- Worked on transcript classification using Qwen-based language-model workflows.
- Built structured JSON extraction from transcripts and supported project coordination.
Megaminds IT
Python Intern
July–September 2024
Python-based academic and research solutions, data preprocessing, and collaboration with the R&D team.
- Implemented research algorithms in Python for academic applications.
- Worked on data preprocessing and contributed to project delivery with the R&D team.
Capabilities in context
What I bring to a team
Backend & asynchronous processing
Python and FastAPI services, with Celery and Redis for background execution. My Tessact work involved job state, retries, idempotency, and recovery for long-running processing.
AI applications
LangGraph agent workflows, conversation context, tool calling, FastMCP server/tool integrations, grounded responses, and streaming — connecting model execution to services and frontend interfaces at FortyGuard.
Systems & infrastructure
Go for HTTP routing and shared state in my load balancer; Docker and Google Cloud Run for service-based processing at Tessact; Linux through my educational OS project.
Connecting AI
to working systems.
At FortyGuard, I help dashboard users ask questions about temperature data and use analysis tools. I connect LangGraph agent workflows to backend services, working on conversation state, tool calling and controlled actions so responses stay grounded in tool results.
I use FastMCP for server and tool integrations through Model Context Protocol (MCP), which lets AI applications access backend tools. Those connections extend to streaming responses and frontend integration, with debugging and end-to-end testing across the workflow.
For temperature-aware routing, the ML team developed the algorithm. My work connects it to backend services and map interfaces through contracts, task execution, hardening and testing.
At Tessact, I also worked on fallback handling for malformed LLM JSON, helping AI output fit a structured processing workflow. My personal projects give me room to explore systems programming, networking, shared state and Linux — from a Go load balancer to educational software.
Explore my personal projectsEducation
BTech in AI & Data Science
AISSMS Institute of Information Technology
Completed May 2026
Let’s talk
Building something useful?
I’m interested in software engineering opportunities across backend systems and AI. If that sounds like your team, I’d like to hear from you.
Email me