1. DautomSenior Software EngineerJan 2025 - Present

   Working on large-scale banking and finance applications used across Mashreq by multiple teams and stakeholders. Contributing primarily to a core application while also working across multiple products and shared application capabilities. - Built and improved large-scale banking and finance applications, working closely with multiple teams and stakeholders across Mashreq. - Introduced IndexedDB-based client-side caching to improve application responsiveness and reduce unnecessary data retrieval. - Built voice-to-text capabilities integrated with LLM workflows, enabling more natural interaction with the application. - Established a reusable shadcn/ui component library to improve consistency and accelerate frontend development across the application. - Built an AI-powered application assistant with knowledge of the product's workflows and functionality, enabling users to ask questions and get guidance about how the application works. - Worked on RAG pipelines to ground AI responses in application-specific knowledge and context. - Worked with MCP (Model Context Protocol) to explore and integrate AI capabilities with application context and tools. - Took ownership beyond individual feature development by handling and coordinating a team of 2–3 engineers, including technical communication and collaboration. - Worked closely with stakeholders and other engineering teams to understand requirements, communicate technical decisions, and deliver application capabilities. - Contributing toward an upcoming end-user-facing product, expanding the scope from internal/enterprise applications toward a product directly used by end users.

   Stack

   • AI Chatbot
   • MCP
   • RAG
   • LangChain
   • Python
   • Agentic Workflows
   • TypeScript
   • React
   • Next.js
   • Node.js
   • Material UI
   • Shadcn UI
   • Optimizations

   Dautom
2. FanorySoftware EngineerMay 2023 - Dec 2024

   As a Software Engineer at Fanory, I have been actively involved in the development of a multi-user application that facilitates meaningful interactions between fans and creators. This innovative platform harnesses a robust tech stack and cutting-edge technologies to create a seamless and engaging experience for our users. 📌 Multi-User Engagement Platform: Spearheaded the development of a multi-user engagement platform that connects fans with creators in real-time. Leveraging GraphQL, we've created a dynamic and responsive system that allows users to interact via live messaging features. 📌 Live Streaming and Video Calling: Implemented live streaming functionalities and video calling capabilities using technologies such as Agora, RTMP, and WebRTC. This enables users to engage with their favorite creators through real-time video interactions. 📌 Content Management: Played a pivotal role in managing and serving diverse content, including photos and videos from creators. Ensured seamless integration of custom content based on artist preferences. 📌 Tech Stack Mastery: Proficiently utilized a comprehensive tech stack, including Amazon Web Services (AWS), Progressive Web Applications (PWAs), MoEngage for notifications, PubNub for real-time messaging, and WebSocket for efficient communication. 📌 Next.js Expertise: Demonstrated proficiency in Next.js, harnessing its latest features such as app routers, server components, and caching functionalities. These enhancements have significantly improved the application's performance and user experience. 📌 Real-Time Interactions: Successfully enabled real-time interactions for fans through live chats, messages, gift stickers, and super-sends. This feature enhances user engagement and facilitates meaningful connections between fans and creators. 📌 Caching with Redis: Implemented Redis caching to optimize data retrieval and enhance application performance. This caching strategy has significantly reduced response times and improved user experience. 📌 CI/CD Pipelines: Designed and implemented robust CI/CD pipelines to ensure smooth and efficient deployment of application updates. This has resulted in faster release cycles and improved reliability. 📌 User Engagement System: Developed a robust system for managing multiple user interactions and engagements. Implemented system notifications through MoEngage to keep users informed and engaged with their favorite creators.

   Stack

   • Amazon Web Services (AWS)
   • GraphQL
   • Progressive Web Applications (PWAs)
   • MoEngage
   • pubnub
   • WebSocket
   • Agora
   • RTMP
   • Webrtc
   • Next.js
   • TypeScript
   • Redux.js
   • Git
3. Pegasus InfoCorpSenior Software EngineerSept 2021 - May 2023

   Client: Azentio software. We have developed and successfully delivered our own product to the banks like PNB, RCBC and more. We have built Mfund application for the banking and finance domain in two years of span. We have added authorisation based on the bank requirements we give them access to some modules or hide some module based on their requirement and the access role of the user. 📌 Successful Product Deployment: In just two years, our dedicated team brought the Mfund application to life for banks such as PNB and RCBC, enabling seamless banking and finance operations in a live environment. 📌 Empowering Financial Planning: As part of the development process, I spearheaded the creation of the Financial Planning module, empowering users to set personalised financial goals, invest wisely, and plan for a secure future. 📌 Advanced Filter Functionality: I developed and engineered an intricate, yet reusable component for the application - the Advanced Filter Functionality. This component features complex logic, enhancing the user experience and optimising data handling. 📌 Performance Optimisation: Recognising the significance of speed and efficiency, I actively worked on optimising the application's performance, streamlining the overall user interface, and ensuring a seamless user journey. 📌 Full Stack Proficiency: My role encompassed both front-end and back-end development. Leveraging technologies like React and Redux, I crafted engaging front-end interfaces, while on the back-end, I designed APIs and skillfully managed databases using Express. 📌 Continuous Enhancement & Bug Fixing: In a dynamic environment, I embraced new challenges with enthusiasm. From adding new functionalities to resolving issues and bugs, my commitment to delivering top-notch solutions remained unwavering.

   Stack

   • Ant Design
   • Next.js
   • TypeScript
   • React.js
   • JavaScript
   • Express.js
   • Redux.js
   • Git
4. FreelanceFull Stack EngineerAug 2020 - Present

   📌 Designing and developing both front-end and back-end components of software products. 📌 Participating in the entire software development lifecycle, from requirements gathering to deployment and maintenance. 📌 Implementing Continuous Integration and Continuous Deployment (CI/CD) pipelines to ensure smooth and automated software delivery. 📌 Containerizing applications using Docker and orchestrating them with Kubernetes for scalability and manageability. 📌 Writing and implementing automation tests, including unit tests, integration tests, and end-to-end tests, to ensure software quality. 📌 Evaluating and selecting appropriate technology stacks and tools for various projects and considering niche technologies for specific scenarios. 📌 Collaborating with cross-functional teams to ensure seamless integration and delivery of software products. 📌 Monitoring and optimizing the performance, security, and reliability of applications in production. 📌 Experienced working with niche technologies, to push the boundaries of innovation and deliver high-value products.

   Stack

   • Prisma ORM
   • PostgreSQL
   • Redis
   • Amazon Web Services (AWS)
   • tRPC
   • Expo
   • Enzyme
   • Jest
   • Jenkins
   • Kubernetes
   • Docker
   • React Native
   • Recoil
   • Continuous Integration and Continuous Delivery (CI/CD)
   • WebSocket
   • RTMP
   • Webrtc
   • Next.js
   • TypeScript
   • React.js
   • JavaScript
   • Node.js
   • MongoDB
   • Express.js
   • Redux.js
   • Firebase
5. BitmanticsFull Stack DeveloperSep 2019 - Sep 2021

   As a dedicated Full Stack Developer at Bitmantics, I embarked on a transformative journey, which built the foundation of my full stack journey. 📌 Exposure to Multiple Domains: - Engaged with diverse clients across various domains, each with unique requirements. - Gained insights into a wide spectrum of industries, fostering a holistic understanding of different operational dynamics. - Adapted to the intricacies of each domain, tailoring solutions to address specific needs. 📌 Problem-Solving and Development Growth: - Confronted and conquered multifaceted challenges, honing my problem-solving skills. - Overcame obstacles through innovative thinking and strategic solutions. - This continuous process of problem-solving transformed me into a versatile and adept developer. 📌 Robust and Scalable Applications: - Designed and developed applications that were not only robust but also tailored precisely to client specifications. - Ensured seamless scalability of systems to accommodate increasing demands. - Delivered solutions within stipulated timeframes, blending quality with timely execution. 📌 Client-Centric Time Management: - Successfully managed time and resources to meet client deadlines without compromising quality. - Prioritised tasks effectively, ensuring on-time delivery of projects. - This client-centric approach solidified my reputation as a reliable and results-driven developer. 📌 Collaborative Client Relationships: - Nurtured collaborative relationships with clients, fostering open communication and understanding. - Acted as a bridge between technical aspects and client requirements, ensuring alignment and satisfaction. - These relationships enriched my ability to translate visions into tangible solutions.

   Stack

   • Recoil
   • Next.js
   • TypeScript
   • React.js
   • JavaScript
   • Node.js
   • MongoDB
   • Express.js
6. AmdocsBusiness and Technical AnalystJul 2018 - Aug 2019

   I had the privilege of contributing to a critical project for Bell Canada. In my role, I gained comprehensive end-to-end knowledge of the Billing Cycle, which was instrumental in ensuring seamless and accurate billing processes for millions of customers, amounting to millions of dollars. Worked on multiple LOBs. 📌 Deep Understanding of Billing Cycle: I gained a thorough understanding of the intricacies involved in the Billing Cycle, encompassing data flow, billing events, and customer invoicing. This expertise enabled me to optimise processes and enhance overall efficiency. 📌 Automation and Krrish Flows: Leveraging my automation skills, I successfully implemented Krrish flows to automate our daily processes. These automation efforts streamlined operations, minimised errors, and accelerated task completion. 📌 Billing Cycle Maps: I played a pivotal role in running and managing jobs within the Billing Cycle Maps, ensuring the smooth execution of billing events and associated processes. 📌 Customer Interaction: My role required direct engagement with on-site customers from Bell Canada. I effectively collaborated with them to understand their specific requirements, address concerns, and provide proactive support. 📌 Efficient Bill Cycle Handling: With a keen eye for detail, I adeptly handled various aspects of the Bill Cycle, including data validation, invoice generation, and billing adjustments. This contributed to accurate billing and enhanced customer satisfaction. My time at Amdocs for the Bell Canada project was an enriching experience, further solidifying my expertise in Billing Cycle Management and honing my ability to deliver exceptional results in a dynamic and customer-centric environment.

   Stack

   • Linux
   • Production Management
   • Scripting
   • Customer Interaction
   • SQL

1. W-01Jev and the Decision Layer: What a System One Model Changes in an AgentA close reading of TypeSafe AI's Jev: state and typed questions in, calibrated Choice, Score, and Noul answers out. What is documented, what is vendor claim, where it fits in an agent, where it does not, and why it complements LLMs rather than replacing them.AI Engineering19 min
2. W-02Who Decides the Next Step: The Anatomy of an AI AgentAn agent is defined by where control flow lives, not by how capable the model is. State and context, planning, observation, memory, verification, recovery, and permissions, and why reliability comes from the software around the model.AI Engineering16 min
3. W-03A Working Method for System DesignA repeatable sequence for designing a system: requirements, rough numbers, interfaces and data, the hard part, failure analysis, and the tradeoffs you are choosing. Worked through on a webhook delivery service.Architecture7 min
4. W-04Distributed Systems Are About Partial FailureEvery remote call has three outcomes, not two. Idempotency, retry budgets, deadlines, quorums, and fencing tokens are what you build once you accept that.Distributed Systems9 min
5. W-05Graph Engineering: Modeling Agent Workflows as Explicit GraphsOnce an agent workflow has branches, parallel steps, approvals, and revision cycles, it is a graph whether or not you draw it. Typed state, nodes, conditional edges, reducers, checkpoints, and how to test and version the result.AI Engineering6 min
6. W-06Harness Engineering: The Software Around the ModelMuch of what users experience as agent behavior is decided outside the model: what context it sees, which tools exist, what they are allowed to do, where they run, and how runs are recorded and judged. A practical guide to building that harness.AI Engineering6 min

1. X-01Jun 17, 2026 / AI Engineering

   90% of AI Engineering interviews in 2026 come down to these 7 points.

   1. LLM Fundamentals: tokenization, transformers & attention, fine-tuning (LoRA/QLoRA), context management, model selection

2. X-02Jun 7, 2026 / AI Engineering

   12 End-to-End AI Engineer Projects in 2026

   1) Production RAG Document Assistant

3. X-03Apr 15, 2026 / AI Engineering

   90% of AI Engineer interviews in 2026 are just these 12 concepts repeated:

   1. Prompt Engineering

   • Zero-shot, few-shot, CoT, ToT, ReAct to steer LLMs

   - Analogy: Giving the chef a super-detailed recipe with exact steps & plating instructions

4. X-04Mar 28, 2026 / Backend Engineering

   As a backend engineer.

   Please learn:

   - One server-side language deeply (Node.js/TypeScript, Python, Java, Go - pick one and master it)

   - API design & development (REST, GraphQL, gRPC, OpenAPI/Swagger, versioning, rate limiting)

5. X-05Feb 9, 2026 / AI Engineering

   Interviewed an Al engineer candidate last week with 8 years in ML for my friend's startup.

   Couldn't explain transformer architecture properly. Didn't know about RAG pipelines. Never worked with vector databases.

6. X-06Jan 24, 2026 / Frontend Engineering

   Interviewed a frontend dev yesterday with 12+ years experience.

   Didn't know about Suspense boundaries in React 19. Struggled with explaining useTransition. Never used Server Components.

• Next JS^{9 listings}
• Typescript^{7 listings}
• React JS^{6 listings}
• Node JS^{4 listings}
• Express JS^{3 listings}
• Javascript^{3 listings}
• MongoDB^{3 listings}
• Redux^{3 listings}
• Agentic systems^{2 listings}
• AWS^{2 listings}
• Git^{2 listings}
• LangChain^{2 listings}
• LangSmith^{2 listings}
• Prisma^{2 listings}
• Recoil^{2 listings}
• Agora^{1 listings}
• AI agents^{1 listings}
• CI/CD pipelines^{1 listings}
• Docker^{1 listings}
• Framer Motion^{1 listings}
• GraphQL^{1 listings}
• Jest^{1 listings}
• LangGraph^{1 listings}
• MCP^{1 listings}
• Mysql^{1 listings}
• OpenAI^{1 listings}
• Postgres^{1 listings}
• Python^{1 listings}
• RAG^{1 listings}
• React Native^{1 listings}
• Redis^{1 listings}
• Tailwind CSS^{1 listings}
• Cloudflare
• CSS
• Drizzle
• Hono JS
• HTML
• Jotai
• Mongoose
• Nginx
• Redux Toolkit
• RPC
• SEO
• Socket.io
• Three JS
• Vitest
• Zod
• Zustand

Clear boundaries.Dependable behavior.Code that can be understood, changed, and operated by someone other than its author.

1. Intro01

   I’m an AI Engineer and Agentic AI Engineer building AI agents and production software. I bring a software engineering foundation to AI work: the interfaces, APIs, data models, and system boundaries that turn a model capability into a product feature.

2. Engineering02

   My background spans frontend and backend product development, API design, databases, architecture, and systems that run in production. I pay attention to how software behaves after it ships: reliability, performance, maintainability, and the operational context around it.

3. Focus03

   My current focus is AI agents and agentic workflows: model interaction, streaming responses, retry behavior, and the boundaries needed to integrate AI into production software.

4. Building04

   I learn by building. I turn questions into working software, put ideas in product context, and refine the parts that fail or feel unclear.

1. S-01

   AI Agent Development

   Build task-focused agents around model interaction, with clear workflow and execution boundaries.

   For teams adding agent capabilities to a product.

2. S-02

   Agentic Workflow Engineering

   Break a task into explicit steps and integrate model interactions with clear retry behavior and handoffs.

   For processes that need more than a single model response.

3. S-03

   AI Product Integration

   Connect model interactions to product interfaces and backend systems, including streaming experiences.

   For products integrating AI into an existing user journey.

4. S-04

   Full-Stack Product Engineering

   Build product features across frontend, APIs, and data layers with production behavior in mind.

   For teams shipping or extending software products.

5. S-05

   System Design and Architecture

   Work through service boundaries, API and data models, performance needs, and implementation trade-offs.

   For teams making consequential technical design decisions.

6. S-06

   Technical Mentoring and Review

   Review code and design choices, and reason through reliability and maintainability with your team.

   For engineers who want a focused technical sounding board.

1. F-0122 Jun 2025
2. F-0204 Jun 2025
3. F-0303 May 2025
4. F-0427 Apr 2025
5. F-0506 Apr 2025
6. F-0617 Mar 2025
7. F-0717 Mar 2025
8. F-0817 Mar 2025

Write to

• Schedule a callCal.com
• MentorshipTopmate, 1:1 session
• LinkedInProfessional profile
• GitHubCode and projects
• XShort notes and updates
• Resumeresume.akshayshinde.com
• Chess.comPlay a game
• SpotifyMusic profile