Software Engineer | Agentic AI | Platform Engineering | Full-Stack Systems

I build practical software systems that combine AI, automation, and reliable backend engineering. My work spans internal tools, production systems, and data-driven applications, with a strong focus on shipping solutions that are useful in real environments.

I’m currently pursuing an M.S. in Software Engineering at San Jose State University. My recent work and projects center on Python, TypeScript, React, Node.js, PostgreSQL, and agentic AI frameworks such as CrewAI and LangGraph.

• 2+ years of software engineering experience across enterprise and product-focused environments
• Experience in production systems, automation, internal tools, and operational workflows
• Strong interest in agentic AI, cloud platforms, data systems, and developer productivity
• I like turning ambiguous problems into simple, dependable solutions through iteration and debugging

• Agentic AI and multi-agent workflows
• Full-stack web development
• Backend services and API design
• Cloud platforms and deployment workflows
• Internal tooling and workflow automation
• Data systems and orchestration
• Production debugging and operational reliability
• Integrating AI into real business processes

Programming Languages Python, TypeScript, JavaScript, Java, SQL, C++

Frameworks and Tools React, Node.js, Express, CrewAI, LangGraph, PostgreSQL, Kafka, Airflow, Docker, Kubernetes, Prometheus, Grafana, ServiceNow, Azure, GCP

AI and Data Work LLMs, RAG, prompt workflows, fine-tuning, agent orchestration, NLP, computer vision, data engineering, analytics

📌 Tech Stack: Python, LangGraph, Google ADK, MCP
🔗 Repo: Multi-Agent-Interop-with-MCP-ADK-A2A-Hands-On-Portfolio

• Explored multi-agent orchestration patterns including tool use, agent-to-agent communication, and interoperability standards
• Reproduced Google codelabs for MCP protocols and ADK workflows, demonstrating practical patterns for scalable agent systems
• Built deployment-ready examples showing how modern AI agents coordinate work across multiple services

📌 Tech Stack: Python, LangGraph, CrewAI, OpenAI
🔗 Repo: AI-Agents-Design-Patterns-using-LangGraph

• Implemented a comprehensive collection of agent architecture patterns: chaining, routing, parallelization, and evaluator-optimizer loops
• Demonstrated real-world patterns for conditional routing, human-in-the-loop workflows, and failure recovery strategies
• Reference guide for building reliable, scalable agentic systems using graph-based orchestration

📌 Tech Stack: Python, LangGraph, React, Node.js, RAG, Vector DBs
🔗 Repo: Build-Full-stack-E2E-Agentic-multimodal-application-with-agentic-rag

• Built an end-to-end multimodal expense assistant combining frontend interactivity with agentic RAG backend patterns
• Integrated document processing, semantic search, and multi-agent retrieval for context-aware responses
• Full-stack deployment showing how agentic AI augments traditional application architecture

📌 Tech Stack: Python, Unsloth, PyTorch, Hugging Face, LLaMA
🔗 Repo: Modern-AI-with-unsloth.ai

• Practical fine-tuning workflows optimizing open-weight LLMs for domain-specific tasks
• Demonstrated memory-efficient adaptation techniques and inference optimization on consumer hardware
• Production-ready patterns for customizing LLMs without massive computational overhead

📌 Tech Stack: Python, Transformers, T5, Hugging Face
🔗 Repo: LegalSummarizer-Fine-Tuned-T5-for-Summarizing-Complex-Legal-Documents

• Domain-focused NLP project fine-tuning T5 for abstractive summarization of legal documents
• Built data preprocessing, model training, and evaluation pipelines for specialized text generation
• Demonstrated transfer learning effectiveness in regulatory and compliance contexts

📌 Tech Stack: Python, Apache Beam, GCP Dataflow
🔗 Repo: ApachBeam-Data-Engineering

• Designed and implemented scalable data pipelines using Apache Beam for batch and streaming workloads
• Demonstrated windowing, aggregation, and state management patterns for data engineering workflows
• Reference implementation of data processing concepts at scale

• Built and supported enterprise systems in regulated and operationally sensitive environments
• Contributed to internal tools, orchestration flows, and automation that improved reliability and speed
• Worked on production debugging, observability, and workflow improvements across service ecosystems
• Applied AI and automation to practical business problems rather than isolated demos

• Agentic AI systems and orchestration
• Platform engineering and internal developer tools
• Cloud-native backend systems
• Data engineering and event-driven architectures
• AI-assisted automation for real business workflows

• LinkedIn: https://linkedin.com/in/manjunathinti
• GitHub: https://github.com/intimanjunath
• Email: manjunatha.inti@sjsu.edu

If you’re hiring, collaborating on agentic AI, or building reliable software systems, I’d love to connect.