Abhiram Shaji
Solutions Architect · Forward Deployed AI Engineering
Montreal, QC, Canada · Open to relocation anywhere in Canada, remote, hybrid, or on site
236-255-3669 · write4abhiram@gmail.com
At Botpress, I take messy problems from the sales team, design the architecture, and build and ship the solution end to end on our SDK. I've become the bridge between enterprise client problems and gaps in our SDK: I solve the problem for the client, then make the solution reusable so the next deployment is faster. That sits on two years of professional engineering across Botpress and Deloitte, building enterprise systems from client problem to production. I do my best work owning the problem with the customer, not coding in isolation. I lean heavily on AI assisted engineering with my own model harnesses, often running parallel subagents under a manager agent.
TypeScript · JavaScript · Python · SQL · Node.js · Botpress ADK · LLM agents · RAG · semantic search · structured extraction · evaluation · REST APIs · webhooks · Docker · CI and CD
Solutions Architect · Forward Deployed
Botpress
Montreal, QC, Canada
- Own and maintain the Botpress monorepo for all enterprise-grade agents, and keep it from decaying by regularly updating it with newer models, techniques, and tips.
- Own the enterprise e-commerce vertical: a Shopify agent kit (search, orders, returns, human handoff, guarded refunds) where one command turns a store URL into a deployed bot that blocks invented facts.
- Built solo and own Agentic Reporter: one Jev call grades each chat for two-sided CSAT, outcome, topic; semantic topics, never hardcoded; prompt edits re-grade only changes; reports reject uncomputed numbers.
- Own 17 enterprise AI deployments and still counting, across North America, Europe, the Middle East and Asia, end to end, from architecture to launch.
- Built the engineering harness the delivery team still ships on.
- Turn recurring client problems into reusable packages, tools, and product patterns.
- Build production agents using tool calling, RAG, semantic search, structured extraction, authentication, long running workflows, and human escalation.
- Built evaluation pipelines that run deployed agents through real channels and grade them with LLM judges.
- Ship across webchat, email, WhatsApp, Instagram, support, CRM, and commerce workflows.
Associate Analyst
Deloitte USI Consulting
Bangalore, India
- Built automation for Aflac that categorized and routed insurance claims requiring revision.
- Built internal dashboards, backend services, and Selenium regression automation in .NET, JavaScript, and SQL.
Built at Botpress and running in production now. Open the site and chat with the agent:
- Yamaha Motor México: yamaha-motor.com.mx
- Visit London: visitlondon.com/things-to-do
- Rentola: faq.rentola.com/hc/en-us/p/chatbot
- YW Calgary: ywcalgary.ca/economic-prosperity
- Dr. Michaels: drmichaels.com
- Upside Drinks: upsidedrinks.ca
- PetsMarket: petsmarket.com
Also shipped for: iolo Technologies · HEAG · IonOptix · Back to the Roots · Monjur · Libertex · Quint · Omniae · Web Arts · TruAbutment · CFL Flooring
Architect, creator and maintainer. An Electron canvas and MCP server that makes a system architecture diagram binding on a coding agent. It must propose every new component, edge, and dependency through the MCP server and wait for visual human approval before writing code. Try it: github.com/abhiramshaji-cyber/Architect
Postgraduate Diploma, Digital Design and Development
North Island College
BC, Canada
Bachelor of Engineering, Computer Science
Bangalore City University
Bangalore, India
Canada Post-Graduation Work Permit (open work permit), valid to Feb 2028
References available upon request.
Dear hiring team,
I'm a Solutions Architect at Botpress, on a lean team where I report to both the Director of Delivery and the Director of Product Engineering. I sit between the client and the code: someone brings me a business problem, I turn it into a working AI agent, and I stay with it long after launch.
Agents I built are running live right now on these sites, so open one and say hello: Yamaha Motor México (yamaha-motor.com.mx), Visit London (visitlondon.com/things-to-do), Rentola (faq.rentola.com/hc/en-us/p/chatbot), YW Calgary (ywcalgary.ca/economic-prosperity), Dr. Michaels (drmichaels.com), Upside Drinks (upsidedrinks.ca), and PetsMarket (petsmarket.com). Others run on Instagram, WhatsApp, Telegram and Gmail, plus a stack of internal API automations. Those are mostly internal, so sadly no peeking. Between them they qualify leads, answer from source documents, and hand off to a human rather than guess.
I own three things: the e-commerce vertical, a Shopify agent kit where one command turns a store URL into a deployed shopping agent that refuses to invent a price; Agentic Reporter (an agent I built solo that grades every client conversation for CSAT in a single Jev call, discovers topics instead of hardcoding them, and writes monthly reports that refuse to print a number they can't prove); and the monorepo behind our enterprise-grade agents. That monorepo has taught me exactly where agents break in production, and I keep it current so agents don't decay and clients don't churn. I own each project from the first client call through production and beyond, and that is the part I enjoy most.
I live in Neovim and work with Claude Code and Pi, wrapped in my own hooks and quality gates, so AI helps me move fast without leaving bloat or slop behind. My favourite side project is Architect (github.com/abhiramshaji-cyber/Architect), an open source tool that makes a coding agent get human approval on the architecture diagram before it adds anything new.
Before Botpress I was at Deloitte USI. I hold a Bachelor of Engineering in Computer Science and a postgraduate diploma in digital design and development. I'm looking for forward deployed, solutions architecture or applied AI engineering work, remote or anywhere in Canada, and I'd love to hear what you're building.
Thank you for reading.
Abhiram Shaji