Download PDF

ROHIT KUMAR

AI Engineer | Generative AI | Agentic Systems | Applied ML

Mohali, Punjab, India | +91 7783805286 | rohitkrsoni1999@gmail.com
linkedin.com/in/rohit-kumar-0993ab232 | github.com/Rohitkumarsony | huggingface.co/rohitkumarai

Professional Summary

AI Engineer with approximately 3 years of experience across AI/ML engineering and backend development. Experienced in building LLM-powered applications, production RAG pipelines and stateful agentic workflows using Python, LangGraph, MCP and FastAPI. Hands-on experience with LLM fine-tuning, retrieval optimization, model evaluation and deploying AI services using Docker and AWS. Focused on building reliable AI systems through controlled tool integration, systematic evaluation and performance optimization.

Technical Skills

Programming & Backend: Python, SQL, SQLAlchemy, FastAPI, Flask, REST APIs, WebSockets, AsyncIO, Celery, Kafka

Generative AI & Agentic Systems: LLMs, RAG, LangChain, LangGraph, LlamaIndex, CrewAI, MCP, Tool Calling, Multi-Agent Systems, Prompt Engineering, SFT, LoRA, QLoRA, Embeddings, LLM Evaluation, OpenAI, Gemini, Claude

AI Systems Engineering: Retrieval Optimization, Vector Search, Latency Optimization, Streaming, Caching, Observability, Vector Databases (Pinecone, ChromaDB, Qdrant, FAISS), Hugging Face Transformers

Machine Learning & Deep Learning: Scikit-learn, PyTorch, TensorFlow, Transformers, CNNs, Transfer Learning, XGBoost, LightGBM, Feature Engineering, Model Training & Evaluation, Hyperparameter Tuning, Computer Vision, OpenCV, SHAP, Time-Series Forecasting

Voice AI: Speech-to-Text (STT), Text-to-Speech (TTS), Streaming Audio, Real-Time Voice Agents, Conversational AI, Voice Activity Detection (VAD), Speaker Diarization, WebSockets, WebRTC, OpenAI Realtime API, Whisper, Deepgram, ElevenLabs, Twilio

Databases & Infrastructure: PostgreSQL, MySQL, MongoDB, Redis, Docker, CI/CD, AWS (EC2, S3), Linux, Git

Professional Experience

Mar 2026 - Jun 2026AI/ML Engineer | Suffescom Solutions Pvt. Ltd.
  • Architected agentic workflows (LangGraph, CrewAI) in which agents reach enterprise systems only through scoped MCP tools, keeping business logic and data access under backend control.
  • Fine-tuned open-source LLMs with SFT and LoRA/QLoRA on domain datasets, improving task accuracy by ~12% on a held-out evaluation set.
  • Built RAG pipelines (Pinecone, ChromaDB) and tuned retrieval, prompts and caching to improve answer accuracy and response time.
  • Shipped Dockerized FastAPI AI services to AWS EC2 with automated testing and performance tuning.
Apr 2024 - Mar 2026Associate AI/ML Engineer | Eminence Internet Technology Pvt. Ltd.
  • Built and ran production RAG for enterprise knowledge retrieval (LangChain, LlamaIndex, Pinecone, ChromaDB), serving millions of queries.
  • Built a real-time voice AI assistant on WebSockets with streaming STT/TTS for conversational interactions.
  • Introduced MCP-based tool calling so LLM agents use internal APIs and databases without direct database access.
  • Designed and deployed Dockerized FastAPI microservices on PostgreSQL and Redis for production use.
  • Automated business workflows with n8n, Zapier and Zoho, eliminating ~10 hours of manual work per week.
Jan 2024 - Mar 2024Software Developer | Code Insects Pvt. Ltd.
  • Built scalable, modular web application features and backend services, following maintainable development practices.
  • Implemented third-party API integrations and robust backend logic to keep application behavior stable and reliable.
  • Worked with development and business teams to turn requirements into working solutions; owned testing, debugging, deployment and maintenance.
Jun 2023 - Sep 2023Software Developer | Shine Dezign Pvt. Ltd.
  • Developed and maintained scalable web applications with a focus on clean backend architecture and REST API integrations.
  • Collaborated with cross-functional teams to deliver features aligned with business requirements.
  • Optimized application workflows, improving system efficiency, performance and user experience.

Selected Projects

AI & Backend EngineerAgentic Trip & Ride Management Assistant

LangGraph, Gemini, FastAPI, MCP, WebSockets, Kafka, Redis, MongoDB, MySQL, Docker

  • Overview: A conversational assistant for ride discovery, booking, cancellation and trip-history queries, over text and real-time voice, where transactional data must stay correct.
  • Design: Stateful LangGraph workflows validate required inputs and route intents. The LLM calls backend-defined MCP tools and never generates or executes SQL. State is split by purpose: Redis for active context, MongoDB for conversation history, MySQL for ride transactions.
  • Integrations: Google Places API for location validation, streaming STT/TTS over WebSockets for voice, and Kafka for asynchronous request ingestion.
  • How it was solved: Profiled LLM, tool-call, database and context-loading latency separately and optimized each, reducing average response time from ~6.5s to ~1.8s. Tool-only database access removed the risk of model-written queries.
AI & Backend EngineerHealthcare AI: Voice-Enabled Appointment Booking

LangGraph, LangChain, FastAPI, MCP, Twilio Voice, OpenAI, Deepgram, ElevenLabs, PostgreSQL, Redis, Docker

  • Overview: A real-time voice AI agent that handles patient appointment booking, rescheduling and cancellation over phone calls.
  • Pipeline: Inbound call (Twilio) → Streaming STT/TTS → LangGraph agent router → Conversation state & memory → MCP tools (EHR, calendar, notifications) → Confirmation → SMS/email.
  • Design: LangGraph workflows for intent detection, patient verification, availability checks and multi-step booking, with persistent per-call state. Dockerized FastAPI services on PostgreSQL and Redis hold conversation state and appointments and run asynchronous workflows.
  • How it was solved: Gave the agent controlled access to EHR, calendar and notification services through MCP instead of direct system access, and kept per-call state so multi-step bookings stay consistent through the call.
Data ScientistSales Decline Root-Cause Analysis & Forecasting

Python, Pandas, statsmodels, LightGBM, SHAP, Prophet, Streamlit

  • Overview: An end-to-end analytics system to find where sales declined, quantify the business drivers and forecast future sales across products, regions and channels.
  • Design: Time-series analysis, statistical testing and feature engineering over price, promotion, product, region, channel and temporal variables. LightGBM with SHAP for driver analysis; Prophet for forecasting.
  • How it was solved: SHAP attributions quantified which drivers explained the decline, and forecasts reached ~9% MAPE under time-based validation. Results were delivered through an interactive Streamlit dashboard.
Machine Learning EngineerVisual Quality Inspection with Deep Learning

Python, OpenCV, PyTorch, Albumentations, Scikit-learn, FastAPI, Docker

  • Overview: An automated visual inspection system that detects product defects from images.
  • Design: OpenCV preprocessing and transfer-learning CNNs, with augmentation for lighting, orientation and image-quality variation.
  • How it was solved: Reached 0.93 precision and 0.91 recall, and tuned the decision threshold on the relative cost of missed defects versus false alarms. Deployed through a Dockerized FastAPI service with defect-localization overlays.

Education

2020 - 2024B.Tech, Computer Science & Engineering | Swami Vivekanand Group of Institutes of Engineering & Technology, Punjab | CGPA: 8.49/10