Portfolio · 2026
Akash Panchal
AI Software Engineer
I build multi-turn agent platforms at Salesforce — the runtime, tools, and memory that turn a model in a loop into something people depend on. On the side I ship voice agents and write code-heavy deep dives on how all of it actually works: the streaming, grounding, and evals that most tutorials skip.
01 / About
The short version
I build agentic AI systems and write about how they actually work. At Salesforce I lead a multi-turn agent platform built on the Mastra Harness — per-thread state, tool catalogs, human-in-the-loop, image generation — the connective tissue that turns a model in a loop into something people depend on.
Nine-plus years and a few platforms deep — Salesforce, Amazon, McAfee — I've shipped systems that serve billions of messages and hundreds of thousands of apps. But the work I care most about now is the part most tutorials skip: the hard problems. Streaming to a real UI, grounding an agent in your own docs, keeping long-running agents alive, proving they're any good, and the brutal timing of voice. I publish deep dives on all of it — with runnable code and real output, no hand-waving.
02 / Experience
Where I've worked
AI Software Engineer, Salesforce
Leading the development of Agentic Content Studio - a multi-turn agent platform for Marketing Cloud.
Key achievements
- Architecting the Agentic Content Studio built using React (frontend), FastAPI (python) and Mastra framework (node).
- Designed the core runtime on Mastra's Harness primitive: per-thread state, observational memory, skills, tools catalog and its APIs, image generation and Human-in-loop.
- Led multiple initiatives for innovation including AI calling, conversational WhatsApp and campaign building.
Stack
Senior Software Engineer - Marketing Cloud, Salesforce
Led the modernization and integration of SMS platforms, serving billions of messages for Marketing Cloud customers.
Key achievements
- Led integration of Marketing Cloud Engagement (MCE) SMS traffic with Unified SMS platform on the Falcon AWS platform — reducing aggregator onboarding time from months to weeks.
- Spearheaded integration of a competitive SMS aggregator across LATAM and East Asian traffic, yielding ~$10M in annual customer saving. (Q3 2024 Quarter Award)
- Architected BYO (Bring-your-own) feature for SMS aggregator, improving cost transparency and platform flexibility.
- Proposed and implemented SMS Aggregator onboarding playbook to automate paperwork, reducing ready-to-onboard from ~16 weeks to ~4 weeks.
- Onboarding new service for migrating existing customers from Private Data Center to Public Cloud (AWS) to provide service resiliency and reduced infra cost.
- Providing mentorship to Juniors for growing to the next level.
Stack
Software Development Engineer 2, Amazon
Software Engineer in the Developer Experience team, solving app certification and publishing problems.
Key achievements
- Contributed to the design and Development of AutoFailure framework that is failure case agnostic to automate developer communication for App testing failures, helped to increase ZTP by ~6.5%.
- Successfully reduced False Negatives of static testing by up to 12%, significantly minimizing the manual efforts required for validating apps.
- Designed and implemented window manipulation for automatic testing of Android Apps on Windows, enabling efficient testing of approximately 200K apps using a unified framework.
- Improved the user experience (UX) for the promotion portal on the App Store retail page and Developer portal, enhancing engagement and visibility.
- Optimized queries and data retrieval time for App details by 50%, resulting in improved performance and response time.
- Mentored an intern, providing guidance and support, and actively contributing to project planning in an Agile environment.
Stack
Backend Software Engineer - Secure Home Platform, McAfee
Spearheaded the development of a custom home security solution for an ISP partner, leveraging a comprehensive tech stack including Python, Go, Cassandra, Redis, DynamoDB, Kafka, AWS, and Terraform.
Key achievements
- Streamlined partner-specific changes by 50% through the implementation of a core solution that generalized custom modifications.
- Resolved critical subscription failure cases, effectively mitigating DDOS-like attacks from routers and ensuring the security and stability of the system.
- Designed and implemented a scalable custom feature-set module to seamlessly support various router models and versions, enabling broader compatibility and ease of integration.
- Optimized the data flow design, resulting in a remarkable reduction of up to 40% in DB storage and network calls for the Router API, significantly improving efficiency and performance.
Stack
Android Software Engineer - Safe Connect (VPN client), McAfee
Played a key role as a Software Engineer in Android, specialising in mobile app development for McAfee's Safe Connect, a security app providing secure network access through a VPN service.
Key achievements
- Created robust VPN interfaces for the Android end-product, ensuring seamless integration and optimal user experience.
- Developed a custom network state-machine to support Auto-start VPN and Activity-log features, enhancing functionality and user convenience.
- Implemented support for Android 8 notification changes via SDK integration, ensuring compatibility with the latest platform updates.
Stack
Backend Software Engineer - Apps scanner, McAfee
Worked as a Software Engineer for the App Scanner team, utilizing technologies such as Python, Flask, XML, MySQL, and MongoDB.
Key achievements
- Implemented optimizations that significantly increased the throughput of the app scanners, reducing repeat scanning of Android apps by up to 5000 per day.
- Designed and implemented a robust pipe-filter service, employing pluggable codes, to efficiently process APK data.
- Helped MySQL fix trigger bug: https://bugs.mysql.com/bug.php?id=87371
- Collaborated with cross-functional teams to ensure seamless integration and optimal performance of the app scanning system.
Stack
Software Engineer Intern, Broadcom Limited
Collaborated with the Bluetooth Software Development team, focusing on Bluetooth Stack for Android OS (AOSP).
Key achievements
- Implemented and enhanced Bluetooth profiles, including AVRCP, MAP, and HID.
- Successfully developed a service layer for AVRCP 1.6 CoverArt within a tight one-month development cycle.
- Engineered a utility code that allowed testing of BLE-only APIs through a mobile app via reverse engineering of AOSP code.
- Provided crucial support for the migration of the Bluetooth stack from Android N to Android M codebase.
Stack
03 / Selected work
Things I've built
VibeFrames
An agentic video composition engine built on a custom Mastra Harness. The agent orchestrates LLM tools and skills to mutate complex timeline state and streams real-time UI updates back through the Vercel AI SDK — a working answer to "what does an agent that edits video actually look like?"
- Mastra Harness
- Vercel AI SDK
- Agentic
- Next.js
- Streaming
Call GPT — Generative AI Phone Calling
A toolkit for building agentic phone calls: Twilio Media Streams wired to an LLM with real-time speech-to-text and text-to-speech. This is where I learned the hard problems in voice — latency, barge-in, turn-taking — the ones no demo warns you about.
- Voice AI
- Twilio
- Real-time
- Node.js
- LLMs
Paymint
A drop-in Paddle payments integration for indie developers — turning days of billing-API wrangling into minutes. Handles checkout, webhooks, and subscription state so you can ship the product instead of the plumbing.
- Payments
- Paddle
- SaaS
- TypeScript
- DX
04 / Writing
Latest deep dives
05 / Contact
Say hi
Building in this space, or want to compare notes on agents? Reach me at akashp1712@gmail.com.