Open to opportunities

ShalinBhatt

AI Engineer | Technical Lead

Staff-level software engineer with 12 years building production-scale distributed systems — from CI/CD pipelines and container orchestration to production AI infrastructure. At STERIS I led platform engineering for a HIPAA-regulated product line at 99.

0+

Years

0

Engineers Led

0K+

Users Served

Scroll

About Me

Staff-level software engineer with 12 years building production-scale distributed systems — from CI/CD pipelines and container orchestration to production AI infrastructure. At STERIS I led platform engineering for a HIPAA-regulated product line at 99.95% uptime and introduced AI-assisted development workflows adopted across a 12-person engineering team.

On my own time, I build autonomous multi-agent systems and AI infrastructure — multi-model orchestration, LLM evaluation frameworks, and observability layers. That is where I push the capability curve.

Engineers Led & Managed (Core team + project teams)

Engineers Hired (Recruited, interviewed, and made hiring decisions)

Team Retention (Industry avg: 60-70%)

Engineers Promoted to Senior Roles (from mentored intern/junior)

Deployed Nationwide

Faster Development via AI Tooling

Work Experience

Technical Lead

Present
STERIS CORP·Richmond, CA
Dec 2021Present
PythonLangGraphOpenAIAnthropicClaudeGroqDockerKubernetesAzurePostgreSQLRedisHexaVue

Senior Software Engineer

STERIS CORP·Richmond, CA
Oct 2017Nov 2021
Ruby on RailsPostgreSQLJavaScriptDockerKubernetesJenkinsLinuxIDSSOR Integration

Certifications & Credentials

Certified Scrum Master (CSM)

Scrum Alliance

2018, Renewed 2023

Becoming a Manager Professional Certificate

LinkedIn Learning

2025

Claude Code 4: Agentic Coding for Professional Developers

Anthropic

2025

Microsoft AI Workshop

Microsoft

2025

Building with AI: Building a Copilot with Azure AI Foundry

Microsoft

2024

Docker Foundations Professional Certificate

Docker, Inc

2026

Agent Skills with Anthropic

DeepLearning.AI

May 2026

Skills & Expertise

Autonomous Agent Systems

Multi-Agent ArchitectureAgent OrchestrationAutonomous Decision SystemsConcurrent Execution & State ManagementSelf-Healing & Failure RecoveryTool Use & Function Calling

Production LLM Engineering

Retrieval-Augmented Generation (RAG)LLM Evaluation FrameworksLLM-as-Judge PatternsMulti-Model Routing & FallbackPrompt EngineeringContext Window Management

AI Reliability & Observability

Agent Workflow TracingProduction AI MonitoringHallucination Mitigation & GuardrailsCustom Evaluation PipelinesLatency OptimizationModel Benchmarking

AI Infrastructure

Vector Databases & Semantic SearchMemory-Augmented ReasoningKnowledge PersistenceContainerized AI DeploymentAPI Design for LLM Systems

Engineering Leadership

Team Management (8-15 Direct Reports)Performance ReviewsTechnical Hiring (10+)Roadmap PlanningCross-Functional LeadershipMentorship & Career Development

Regulated & Enterprise Systems

HIPAA ComplianceAudit TrailsZero-Downtime DeploymentSecurity-First ArchitectureEnterprise Scale

Systems & Distributed Infrastructure

Distributed Systems DesignCI/CD Pipeline ArchitectureContainer Orchestration (Kubernetes)Zero-Downtime DeploymentsLinux Systems AdministrationObservability & Monitoring (Prometheus/Grafana)PostgreSQL & Redis at ScaleEvent-Driven Architecture

Technical Stack

PythonGoJavaLangGraphLangChainOpenAIAnthropicClaude (Anthropic)GroqOllamaChromaDBFastAPIDockerKubernetesLinuxAzurePostgreSQLRedisRuby on RailsgRPCGraphQL

Featured Projects

Autonomous Multi-Agent Trading System

Proprietary · Production

Production multi-agent system for autonomous trading across multiple brokers. Built with Python, LangGraph, and multi-model AI orchestration.

PythonLangGraphMulti-Model AI

Local AI Application Suite

productionAI/ML

Privacy-focused 4-app AI platform running 100% locally: Personal AI Assistant (multi-model chat & image generation), Code Documentation Generator (auto-docs for any codebase), Local RAG System (semantic search with citations), and AI Image Classifier (auto-tagging & face recognition). Fully containerized with Docker. Demonstrates production-ready AI architecture for enterprise privacy requirements.

ReactTypeScriptFastAPIOllamaChromaDBDocker

LLM Eval Harness

productionAI/ML

LLM evaluation framework with LLM-as-judge pattern, consistency testing, and RAG evaluation. Built 6 automated evaluators (accuracy, consistency, latency, cost, LLM-as-judge, RAG quality) with multi-provider runners for model selection at scale.

PythonSentence TransformersPyTorchClickOllamaOpenAI API

AI Observe

productionAI/ML

AI observability layer for production LLM applications. Decorator-based agent workflow tracing, web dashboard with timeline visualization, and framework integrations for Ollama, CrewAI, and LangChain to make AI decisions transparent and debuggable.

PythonFastAPISQLAlchemyJinja2SQLitePostgreSQL

Surface Pro Arch Linux Configuration

workingDevTools

Complete Arch Linux setup with GNOME for Microsoft Surface Pro devices. Includes custom kernel patches, hardware optimization scripts, and configuration for touch/stylus support. Addresses Surface-specific challenges like firmware, battery management, and type cover integration.

Arch LinuxGNOMEShell ScriptingKernel Patchingsystemd

Claude Chat Export

workingBrowser Extension

Chrome extension for exporting Claude AI conversations to markdown, JSON, or text format. Built to preserve important AI interactions for documentation and knowledge management workflows.

JavaScriptChrome Extensions APIDOM ManipulationMarkdown

DevTab Manager

workingBrowser Extension

Developer-focused tab management Chrome extension for organizing browser sessions, saving workspace states, and quickly restoring development environments. Reduces context-switching overhead for multi-project workflows.

JavaScriptChrome Storage APISession ManagementIndexedDB

Copy as Markdown

workingBrowser Extension

Chrome extension that converts web page selections to clean markdown format. Preserves formatting, links, and code blocks for seamless documentation workflows.

JavaScriptClipboard APIHTML ParserMarkdown Converter

JournalStylus

workingWeb App

Personal journaling application with stylus and touch support for natural writing experience. Features daily entries, mood tracking, and searchable history for mindful reflection and personal growth.

JavaScriptHTML5 CanvasLocal StorageTouch EventsPWA

Open Source Contributions

OpenCode

2026

Contributed bug fixes for terminal UI stability and session management.

GoTUI

Multica

2026

Contributed Linux desktop integration fixes including native file handling and window management.

TypeScriptElectronLinux

Zen Browser

2026

Contributed fixes for tab management and window state handling.

TypeScriptCSSBrowser

Zorin OS

2026

Contributed fixes for Linux desktop integration and system-level improvements.

LinuxShellSystemdGNOME

My AI Philosophy

I build autonomous multi-agent systems — not just prompts glued together, but real architectures with concurrent execution, self-healing failure recovery, and intelligent orchestration that makes decisions independently.

Production LLM infrastructure is a different discipline than notebook experiments. It demands evaluation frameworks, hallucination mitigation, observability layers, and multi-model routing with fallback logic — all running reliably at scale.

The frontier is where capability meets reliability. I push the curve by building systems that don't just demonstrate AI concepts — they ship them into production with guardrails, monitoring, and measurable impact.

Built from scratch, not just in notebooks

Get in Touch

I'm always open to discussing AI engineering, leadership opportunities, or interesting projects. Feel free to reach out.