Skip to content
Open to roles & agentic-AI builds

Atharva Pingale

>I buildagentic systems

I build agentic AI systems that hold up in the real world — multi-agent orchestration, persistent memory, and the infrastructure to ship them safely.

View work Résumé Get in touch

~/ based in Columbus, OH · 4+ yrs · M.Eng CS · GPA 4.0

01about

Engineering AI that earns trust in production

I'm an AI/ML and full-stack engineer with 4+ years shipping agentic systems — the kind that have to be correct, auditable, and fast when real people and regulated data are on the line.

Most of my work lives at the intersection of multi-agent orchestration, persistent memory, and the infrastructure that lets teams ship agents safely: grounding responses in real domain data, gating quality with continuous evals, and enforcing guardrails from day one rather than bolting them on later.

I've built across healthcare, fintech, and regulated enterprise environments — distributed backends, event-driven pipelines, large React/TypeScript frontends, and data platforms scaled from zero to tens of thousands of integrations.

I work fast and I raise the floor around me — building reusable patterns and tooling so non-AI engineers can extend what I ship, and leaning on AI coding tools daily to move from research to working pipeline quickly.

now
Software Engineer, Big Kitty Labs
based
Columbus, OH
education
M.Eng CS · GPA 4.0 · Univ. of Cincinnati
domains
Healthcare · Fintech · Regulated enterprise
tooling
Claude Code · Cursor · Copilot, daily
selected outcomes — measured in production
0%
Lower perceived latency
TTFB cut via Kafka + Server-Sent Events vs. REST polling
0%
Faster analytics
Query rewrites & partitioning across Presto, Trino, BigQuery, Spark
0K+
Integration points
Scaled a data platform from MVP to 10,000+ in 6 months
0%
Data-quality compliance
Automated governance framework for regulated enterprise clients
0.0
Graduate GPA
M.Eng Computer Science, University of Cincinnati
02experience

Experience & education

Four-plus years across agentic AI, distributed backends, and large-scale data platforms.

Work experience

  1. Software Engineer · Big Kitty Labs

    May 2024 — Present

    Columbus, OH

    Architecting agentic AI systems — and the infrastructure to run them safely — across consumer apps and regulated enterprise portals.

    • Architected multi-agent orchestration pipelines in LangGraph & LangChain with MCP tool integrations, structured output schemas, and safe tool execution for complex multi-step reasoning.
    • Built persistent memory over pgvector and Graphiti knowledge graphs, grounding LLM responses in domain data and cutting hallucinations on high-stakes queries.
    • Stood up CI/CD for agents with automated LangSmith eval harnesses — gating task success, grounding, latency, and drift on every deploy.
    • Shipped enterprise safety guardrails and anti-jailbreak middleware with strict tenant isolation and audit-ready access logging.
    • Built Kafka + SSE event streaming that cut perceived latency (TTFB) by 50% versus REST polling, plus real-time observability dashboards.
    • Owned large React/TypeScript frontends (Redux, Zustand, Jotai) and the build/test tooling (Vite, esbuild, Vitest) across the codebase.
    LangGraphLangChainMCPpgvectorFastAPIAWSKubernetesKafkaReactTypeScript

  2. Software Engineer · Angular Minds

    Nov 2021 — May 2023

    Remote

    Built full-stack data platforms and AI-powered workflow tools at scale across healthcare and regulated enterprise environments.

    • Built a full-stack data platform from zero to 10,000+ integration points in 6 months across AWS, Azure, and GCP, serving millions of daily requests.
    • Engineered a Neo4j knowledge graph linking millions of entities for dependency analysis, impact tracing, and relationship-aware ML features.
    • Diagnosed and resolved bottlenecks across Presto, Trino, BigQuery, and Spark — cutting critical analytics execution time by 40%.
    • Shipped an automated data governance framework reaching 99% data-quality compliance with full audit trails and auto-correction.
    • Operated Airflow pipelines ingesting hundreds of external APIs under strict privacy and compliance controls.
    • Delivered HIPAA-aligned clinical workflow tools and interactive BI dashboards in React & TypeScript.
    PythonJavaC#/.NETNeo4jAirflowPresto/TrinoPostgreSQLReact

  3. + earlier engineering experience

Education

M.Eng, Computer Science

Dec 2024

University of Cincinnati

GPA 4.0

B.E., Computer Engineering

Savitribai Phule Pune University

03work

Selected work

Flagship case studies plus open-source tools. Client work is presented anonymized.

Agentic AIRAG
2025

Persistent Agentic Memory

Grounded LLM agents in domain data with pgvector + a Graphiti knowledge graph, cutting hallucinations on high-stakes queries.

LangGraphpgvectorGraphitiPostgreSQL
Case study
Agentic AIInfra
2025

CI/CD & Eval Harness for Agents

Operationalized agent evaluation — gating task success, grounding, latency, and drift on every deploy with LangSmith.

LangSmithGitHub ActionsPythonDocker
Case study
Agentic AISecurity
2025

Jailbreak Defender

Open-source anti-jailbreak middleware and safety guardrails for LLM systems.

PythonLLM safety
Code
FrontendOSS
2024

NER Visualizer

Interactive tool for visualizing named-entity recognition output, built in TypeScript.

TypeScriptReactNLP
Code
04stack

Tools of the trade

The day-to-day stack, plus the broader toolkit I reach for across AI, backend, data, and frontend.

core stack
PythonTypeScriptLangGraphLangChainFastAPINext.js / ReactPostgreSQL / pgvectorAWSKubernetes

AI & Agents

LangGraphLangChainMCP workflowsRAG pipelinesMulti-agent orchestrationPersistent memory & contextLLM APIs (OpenAI, Anthropic)Prompt engineeringAgent evaluation (LangSmith)Responsible AI

Languages

PythonJavaTypeScriptJavaScript (ES6+)SQLC# / .NETBash

Backend & APIs

FastAPIFlaskREST APIsMicroservicesEvent-driven architectureKafkaNode.jsGraphQLWebSocketsServer-Sent Eventspytest / JUnit

Frontend & UI

ReactNext.jsReduxZustandJotaiData visualizationReal-time dashboardsViteesbuildTesting Library / Vitest

Data & Databases

PostgreSQLpgvectorNeo4j (Cypher)RedisMongoDBPresto / TrinoBigQuerySpark (PySpark)AirflowQuery optimization

Cloud & Infra

AWS (ECS, S3, Lambda, EMR)GCP (BigQuery, Dataproc)AzureDockerKubernetesTerraformGitHub ActionsGrafana / observability

Security & Compliance

HIPAA-aligned environmentsData governance frameworksAudit trailsAnti-jailbreak middlewareTenant isolation21 CFR Part 11 adjacent
daily ai tooling
Claude Code/Cursor/GitHub Copilot/research/prototyping/code review/Claude Code/Cursor/GitHub Copilot/research/prototyping/code review/Claude Code/Cursor/GitHub Copilot/research/prototyping/code review/Claude Code/Cursor/GitHub Copilot/research/prototyping/code review/

Currently building

updated June 2026
  • Building reusable agentic workflow patterns and a plugin distribution system so non-AI engineers can ship agents independently.
  • Deepening eval coverage — grounding, drift, and latency gates wired into CI/CD for every agent deploy.
  • Exploring on-prem inference and model versioning/rollback for regulated enterprise environments.
Follow along on GitHub
05contact

Let's build something agentic.

Hiring, collaborating, or just want to talk shop about agents and infra? My inbox is open.

Drop a note with the form — it reaches me directly, and I reply to everything.

Columbus, OH · open to remote

find me