The Architect

Biography, trajectory, and operating principles

Architect of systems. Builder of intelligence.

Scale: 1:1
Rev: C
Issued: 2026.09

I work where product stakes, model behavior, and infrastructure meet. The through-line in my career is taking ambiguous domain problems (multi-tenant fertility platforms, defense-adjacent video intelligence, and clinical NLP) and making them operable.

Technically, I live in the stack you actually run in production: LLMs and SLMs, agentic orchestration, hybrid RAG, schema-grounded NL2SQL, FastAPI, React, Kafka, Docker, and AWS CDK. I care about evaluation, cost-aware routing, and the boring parts: JWT auth, audit logs, and Playwright regression. That is what separates a demo from something a C-suite can sign off on.

Chronology

2021–2023
MSc Artificial Intelligence
Lviv Polytechnic National University
Graduated with Distinction (9.8/10). Master's thesis on Alzheimer's disease classification benchmarking 9 machine learning models on longitudinal biomarkers.
2023–2025
Data Scientist II
Insurance · Document Intelligence
Shipped document intelligence on AWS Bedrock (Claude, LayoutLMv3) achieving 95%+ extraction accuracy. Built ensemble underwriting models improving efficiency by 78%.
2025
Founding Engineer
Restaurant SaaS
Validated demand forecasting across 200+ pilot sites using XGBoost and Prophet, reducing food waste by 32%. Scaled event-driven pipelines to process 2M+ events/day.
2025–2026
Senior AI Consultant
Finance & Healthcare
Built stateful LangGraph finance workflows reducing manual touchpoints by 60%. Deployed multimodal clinical pipelines (QLoRA, hybrid RAG) on HIPAA-aware AWS, maintaining sub-800ms p95 latency.
2026
AI Lead
Defense-Adjacent · Video Intelligence
Architected an agentic video-intelligence platform over 24/7 CCTV using LangGraph and MCP, cutting analyst intervention by ~70%. Engineered Kafka ingestion for sub-200ms latency on air-gapped infrastructure.
2026–Present
Lead Full-Stack AI Engineer
Forward Deployment · Multi-Tenant AI
Owning roadmap-to-production across multiple client programs. Architecting shared LLM gateways, governed reporting agents, and Python microservices on AWS CDK. Delivering multi-tenant workflows that survive C-suite UAT.

Fig. 1Elevation along the career datum. Choose a volume to read the role; each stands on the one before.

This site is a thinking laboratory: case studies, technical writing, and essays that mirror how I negotiate scope, architecture, and delivery. Organization names are generalized on this site; the engineering is specific. For AI systems, forward-deployed engineering, or performance-critical products, get in touch.

A-101record

sheet: A-101
title: The Architect
subtitle: Biography, trajectory, and operating principles
discipline: A · Architectural
scale: 1:1
revision: C
issued: 2026.09
refs: R-301, W-400, C-700
name: Akshay Bajpai
role: Senior Full Stack AI Engineer · Forward Deployment
based: New Delhi, India

General arrangement

G-000 Key Plan — General arrangement of the complete set
A-101 The Architect — Biography, trajectory, and operating principles
R-301 Research — Published work and experimental directions
S-201 Structural Principles — The decisions that outlast implementation
W-400 Works — Case studies, as built
E-600 Essays — Longer arguments about systems, cost, and trust
B-500 Field Notes — What the work taught, written down while it was fresh
C-700 Correspondence — Open a line

Works · details

W-401 Forward-Deployed: Multi-Tenant Fertility & Surrogacy AI — Three coordinated chatbots, a governed NL-to-SQL reporting agent, and a shared LLM platform layer across multiple client programs, with a roadmap to production on AWS CDK.
W-402 AIDA: Health Programme Intelligence You Can Brief From — Turning facility assessment rows into screening rates, management gaps, and district rollups, with optional LLM narratives that never invent the numbers.
W-403 Agentic Video Intelligence for 24/7 Operations — Real-time CCTV triage with LangGraph and MCP: Kafka ingestion, sub-200ms paths, and defense-grade on-prem deployment.
W-404 Neural Map Personal Site: Spatial Navigation as Homepage — A scroll-driven Three.js constellation where clusters replace nav bars, with hover, fly-in, and iframe overlays for essays, work, and writing.
W-405 AURIXA: Conversational AI Orchestration at Scale — Multi-tenant microservices platform for real-time LLM routing, RAG, agent execution, safety guardrails, and voice, built as a production Turborepo monorepo.
W-406 Alzheimer's Classification: Master's Thesis Research — Benchmarking nine machine learning models on OASIS longitudinal biomarkers for dementia detection: rigorous preprocessing, grid search, and clinical interpretability.
W-407 Agentic Finance & Multimodal Healthcare AI — LangGraph workflows across portfolio logic and onboarding, plus QLoRA clinical imaging pipelines on HIPAA-aware AWS with hybrid RAG at sub-800ms p95.
W-408 Publishing AI Automation: Multi-Channel Support at Scale — Multi-channel author query automation with intent classification, hybrid RAG, unified identity across WhatsApp and email, and confidence-gated human escalation.
W-409 Restaurant SaaS Forecasting at Scale — Founding-engineer delivery for inventory and demand sensing: XGBoost and Prophet, Node APIs, Next.js ops dashboard, and 2M+ events/day pipelines.
W-410 Insurance Document Intelligence on AWS — Multimodal RAG, Claude and GPT-4 Vision, LayoutLMv3 extraction, and ensemble underwriting models: 95%+ accuracy at 10K+ queries/day.
W-411 Clinical NLP from Unstructured EHRs — BioBERT and spaCy NER pipelines extracting 47+ structured variables at 91.5% accuracy, across 5K+ documents/day, with risk scoring at scale.

Essays · details

E-601 The Model That Refuses to Draw — Generative models predict pixels; JEPA predicts what the pixels mean. Why the refusal to reconstruct is the most important architectural decision in world models, and what it teaches anyone who builds systems.
E-602 Minimalism as Engineering — Why less is more in system design: fewer dependencies, fewer features, fewer moving parts, and how to get there without sacrificing capability.
E-603 The Architecture of Trust — How system design either builds or erodes trust, and what to optimize for when the user can’t see inside the black box.
E-604 Why Performance Is a Feature — Performance is not a nice-to-have. It’s a product requirement that affects conversion, retention, and trust. Here’s the case and the practice.
E-605 The Cost of Convenience — Why every dependency and every abstraction has a price, and how to pay it consciously.
E-606 What Systems Thinking Actually Is — A long-form look at systems thinking: feedback loops, leverage points, and why it’s a discipline, not a buzzword.

Field notes · details

B-501 Reinforcement Learning After the Reward Model — How reasoning models are actually trained now: verifiable rewards instead of learned ones, GRPO and its descendants, RL compute that scales on a curve, and agents trained inside environments. With the engineering lessons for anyone shipping LLM systems.
B-502 World Models, As Issued: The State of the Set in October 2026 — A field survey of where world models actually stand: V-JEPA 2.1, LeJEPA, Dreamer 4, Genie 3, Marble and Atlas, Cosmos, and a billion-dollar bet in Paris. What shipped, what it cost, and what it is for.
B-503 Experimental UI as an Engineering Discipline — Why treating experimental UI and creative front-end as engineering, not “designer code”, raises the bar for both art and performance.
B-504 Architecture Design for Healthcare AI — How to design AI systems in healthcare: compliance, safety, and the primacy of the clinician in the loop.
B-505 AI in Restaurant Automation — Where AI actually helps in restaurant operations, order prediction, inventory, and kitchen flow, and where it’s hype.
B-506 Systems Thinking for Founders — Why founders who think in systems ship better products and make fewer irreversible mistakes.
B-507 Performance Engineering on Static Hosting — How to hit Lighthouse 95+ and sub-second FCP when you have no server: budgets, critical path, and discipline.
B-508 Building SaaS with a Zero-Dependency Mindset — Why minimizing dependencies is a strategic advantage in SaaS, and how to do it without reinventing the wheel.
B-509 DNS-Level Ad Blocking. System Design — How to design a DNS-based ad blocking system: architecture, tradeoffs, and what you give up when you block at the resolver.
B-510 AI Infrastructure Philosophy — Why the best AI systems treat infrastructure as a first-class product, and how to think about reliability, scale, and operator experience.

Chronology

MSc Artificial Intelligence

Data Scientist II

Founding Engineer

Senior AI Consultant

AI Lead

Lead Full-Stack AI Engineer