AI Engineer
Independent systems
I design and build agent runtimes, memory systems, tool integrations, evaluation workflows, and AI interfaces.
AI engineer · Data analyst at Baselane · Toronto
I build AI systems with memory, tools, and reliable workflows.
I’m Krrish. I work as a data analyst at Baselane and design AI systems focused on agent architecture, orchestration, evaluation, and the data underneath them.
Agent architecture✦Agent loops & orchestration✦Memory & retrieval✦Prompt & context design✦Tools & automations✦Evaluation & observability✦Applied machine learning✦
Selected work
AI systems, models, and the decisions behind them.
Case studies on agent architecture, machine learning, evaluation, and the trade-offs that shaped each system.
AI systems
Current work in agents, memory, tools, and operations.
/01
Self-hosted agent runtime · Claude Agent SDK
A self-hosted multi-agent runtime built around the way I actually work.
A multi-channel agent runtime with persistent memory, task-scoped subagents, voice, tools, automations, recovery, and an operations dashboard.
- 4 interfaces
- 2 memory layers
- 3-pass consolidation
Applied ML and simulation
Earlier work in modelling, evaluation, and decisions.
/02
Machine learning · Python
A fraud detector designed around the cost of being wrong.
A risk-focused model for a heavily imbalanced dataset, built to catch more fraud without burying reviewers in false alarms.
- <0.2% fraud
- ~84% CV F1
- 0.4 review threshold
/03
Predictive analytics · Python
Turning churn predictions into business decisions.
Feature engineering, model comparison, and business analysis for finding which customers may leave and what a retention team could do next.
- 10k customers
- 6 models
- 0.63 F1
/04
Simulation · R
72,000 possible retirements, one clearer decision.
A Monte Carlo model testing when Canadians should draw OAS under different lifespans, account types, tax rules, and market conditions.
- 72k simulations
- Ages 65–70
- RRSP + TFSA
Experience
Business context, data fluency, AI engineering.
My work combines business judgment, analytical depth, and hands-on system building.
Data Analyst
Baselane · Toronto
I work with data, analysis, and reporting to help teams make clearer decisions.
BBA
Schulich School of Business
Built a foundation in business analytics and finance before moving deeper into technical work.
Writing
Writing from the work.
Technical notes, project breakdowns, mistakes, and ideas I want to revisit.
Note 002Read note →Note 001Read note →
Browse all writing Systems notes · 8 min read
Building a self-hosted multi-agent runtime
Model notes · 5 min read
What ROC-AUC hid in my fraud-detection project
The throughline
Business → Data → AI systemsI bring business judgment and data discipline into the way I build AI systems.
I studied business analytics and finance at Schulich and now work as a data analyst at Baselane. That background keeps me close to the decisions, constraints, and people behind the technology.
My focus is AI engineering: agent architecture, memory and retrieval, prompt and context design, tool use, evaluation, and interfaces that make complex systems easier to operate.