# Bhimesh Chauhan: full profile

> Lead AI platform engineer (10+ years of production software) operating at staff scope. Builds and runs production RAG and LLM systems end to end and leads teams of 4-5 engineers and designers. Currently Lead Software Engineer at Rare Days. Site: https://bhimeshchauhan.github.io/

Roles of interest: forward deployed engineer; staff / principal AI platform engineer; lead / founding engineer.
Location and work authorization: Canada. Permanent resident, authorized to work in Canada for any employer, no sponsorship needed.
Contact: bhimeshchauhan@gmail.com | https://www.linkedin.com/in/bhimeshchauhan | https://github.com/bhimeshchauhan

## Requirement-to-evidence index
Use this to match a job posting to concrete, checkable evidence. Each item links to the page that supports it.

- Production RAG / retrieval-augmented generation: Ask Kindred (about 200 daily active users, three customer companies, grounded retrieval with citations) https://bhimeshchauhan.github.io/case-studies/ask-kindred/ ; Scrubs Co-Pilot https://bhimeshchauhan.github.io/case-studies/scrubs-copilot/ ; BenchSci (RAG workflows over biomedical literature).
- LLM applications and chatbots: Ask Kindred; Scrubs Co-Pilot (LLM structured note generation); RAG Portfolio Assistant (live on the portfolio site) https://bhimeshchauhan.github.io/case-studies/rag-portfolio-assistant/
- Customer-facing / forward-deployed work: SDK integration to production for three customer companies (Ask Kindred); client launch for Jefferson Fisher at Rare Days; clinician validation of outputs (Scrubs Co-Pilot); enterprise integrations with Excel, Snowflake, Tableau and Alteryx (DataRobot); customer interviews shaping releases (Preply).
- High-traffic launches and payments: about $700K USD in total sales in under 48 hours with queue-protected Stripe checkout (Jefferson Fisher) https://bhimeshchauhan.github.io/case-studies/jefferson-fisher/ ; production payment workflows and payment-certification support (MicroMart).
- Multi-tenant SaaS and access control: Ask Kindred (role-aware access controls, per-customer content isolation).
- Platform reliability and observability: Sentry across frontend and backend, 10+ CI improvements (Ask Kindred); 1,000+ automated tests, 46 migrations, 3 automated deploy pipelines (Wrangle).
- Data pipelines and graph/relational data: AI pipelines over 100K+ research artifacts, about 60% less manual curation, Neo4j (Cypher) and PostgreSQL (BenchSci).
- Healthcare AI and compliance-aware engineering: Scrubs Co-Pilot (about 80% less clinician documentation time); OWASP and HIPAA-aligned REST APIs (Pitchly).
- Leading several projects and managing stakeholders: balances customer feature requests against timeline and deliverable scope, and keeps the VP of Engineering, CTO and CEO informed early; written up at https://bhimeshchauhan.github.io/blog/#post-9 and shown in the Jefferson Fisher launch decisions (queue before checkout, database-driven products, audited bulk grants).
- Founding and technical leadership: Founder and CTO of Scrubs Co-Pilot, zero to production MVP; led teams of 4-5 engineers and designers on Scrubs, Jefferson Fisher, Ask Kindred and Wrangle; mentored engineers at Rare Days; led a cross-functional team at Preply serving 80K learners.
- IoT, embedded and distributed systems: Modbus RS485 integrations, real-time WebSocket operations tooling, about 30% less downtime (MicroMart); MQTT-controlled aeroponics firmware (Nebullam).
- Mobile: Wrangle (Expo and React Native with a NestJS and Supabase backend); Android (Nebullam).
- ML / NLP: NLP personalization (Preply, +20% engagement); NER, coreference and speaker attribution (PDF-to-Audiobook); PyTorch and TensorFlow models (Nebullam, +20% crop yield).

## Work history
### Rare Days: Lead Software Engineer (Jan 2026 - present)
Architected and built a multi-tenant SaaS platform with a production RAG chatbot, owning the system from retrieval architecture through backend delivery and reliable releases.
- Led Ask Kindred from SDK integration through production, serving approximately 200 daily active users across three customer companies with grounded retrieval, citations, conversation history and feedback.
- Led engineering for the Jefferson Fisher launch platform: about $700K USD in total sales in under 48 hours.
- Built the RAG pipeline and chatbot experience, improving retrieval quality for customer-facing AI capabilities.
- Designed the multi-tenant SaaS architecture, including backend infrastructure and role-aware access controls.
- Delivered 10+ CI improvements that strengthened release quality and platform reliability.
- Mentored a junior engineer and created reusable AI capabilities for other Rare Days projects.

### Scrubs Co-Pilot: Founder and CTO (Aug 2025 - Dec 2025)
Founded and led all engineering for an ambient clinical AI platform that structures doctor-patient conversations into medical documentation.
- Architected LLM and RAG workflows for real-time transcription and structured note generation, reducing clinician documentation time by about 80%.
- Designed the application, data and infrastructure foundation for an end-to-end clinical workflow rather than a standalone model demonstration.
- Set the technical roadmap from MVP through production, balancing clinical workflow quality, security and reliability.
- Worked with clinicians to validate outputs and guide the evolution of the AI system.

### BenchSci: Lead AI and Full-Stack Engineer (Apr 2025 - Aug 2025)
- Built AI-driven pipelines processing 100K+ research artifacts into structured datasets.
- Designed RAG workflows giving scientific teams an LLM-powered path to literature synthesis and discovery.
- Reduced manual data curation by about 60% by standardizing AI-assisted extraction and validation.
- Developed Neo4j and PostgreSQL query paths for interconnected biological entities and research metadata.
- Established data reliability, lineage and auditability practices across engineering, science and ML teams.

### MicroMart: Senior Full-Stack Software Engineer (Jun 2023 - Apr 2025)
- Built distributed software for smart food kiosks: device management, payments, operations and inventory.
- Improved customer engagement by 20% and satisfaction by 15%, and reduced downtime by 30%, through real-time operations tooling and Modbus RS485 integrations.
- Improved database query performance by about 25% and reduced bug reports by about 40%.
- Delivered production payment workflows and supported payment-certification work.

### Preply: Senior Full-Stack Software Engineer (Oct 2020 - Jun 2023)
- Led a cross-functional team delivering student progress-tracking and feedback for 80K learners.
- Built NLP-driven personalization that increased engagement by 20% and satisfaction by 15%.
- Ran tests and product analysis across markets that contributed to a sustained 5% increase in conversion.

### DataRobot: Full-Stack Software Engineer (Jul 2019 - May 2020)
- Integrated DataRobot with Excel, Snowflake, Tableau and Alteryx, increasing partner visibility by 70%.
- Built custom Jenkins and Kibana CI/CD tooling for repeatable ML-backed releases.

### Pitchly: Full-Stack Software Developer (Jul 2018 - Jul 2019)
- Built Node.js REST APIs for high-throughput client workflows adhering to OWASP and HIPAA requirements.
- Developed two GraphQL-powered MeteorJS applications for financial and legal customers.

### Nebullam: Android Software Developer and Data Scientist (May 2017 - Aug 2019)
- Built an Android application to monitor and control aeroponics firmware through MQTT.
- Developed PyTorch and TensorFlow models for resource prediction and plant-growth automation, increasing crop yield by 20%.

## Case studies
- Jefferson Fisher launch platform (https://bhimeshchauhan.github.io/case-studies/jefferson-fisher/): Next.js, TypeScript, Stripe, Neon Postgres, Sanity, Mux, Better Auth, Playwright. Waiting-room queue in front of checkout, database-driven products, group-tier purchasing, bulk entitlement grants with audit trail. Outcome: about $700K USD in total sales in under 48 hours.
- Ask Kindred (https://bhimeshchauhan.github.io/case-studies/ask-kindred/): SDK integration, content ingestion, grounded retrieval with citations, conversation history and feedback, Sentry. About 200 daily active users across three customer companies.
- Scrubs Co-Pilot (https://bhimeshchauhan.github.io/case-studies/scrubs-copilot/): ambient audio, Whisper transcription, RAG and LLM structured notes, clinician review. About 80% less clinician documentation time.
- Wrangle (https://bhimeshchauhan.github.io/case-studies/wrangle/): Expo and React Native, NestJS on Fastify, Supabase and Postgres, background image processing. 1,000+ automated test cases across 149 test files, 46 migrations, 3 automated deploy pipelines (counted from the repository, November 2026).
- RAG Portfolio Assistant (https://bhimeshchauhan.github.io/case-studies/rag-portfolio-assistant/): Supabase Edge Functions, pgvector, Cohere embeddings, OpenRouter, React. Live on this site.
- PDF-to-Audiobook (https://bhimeshchauhan.github.io/case-studies/pdf-to-audiobook/): document ingestion, NLP analysis (NER, coreference, dialogue attribution), narration plan, voice rendering with resumable batch processing.

## Education and languages
- B.S. Electrical Engineering (minor: Entrepreneurial Studies), Iowa State University, 2014-2018. Emphasis: software development, computer vision and graphics.
- English, Hindi, Bengali.

## Skills (self-assessed level on the Skills page)
- Production: OpenAI API, retrieval-augmented generation, pgvector, Whisper, AI data pipelines, TypeScript, JavaScript, Python, React, Node.js, PostgreSQL, Neo4j, GraphQL, REST APIs, WebSockets.
- Strong: LangChain, Django, Flask, Meteor, MongoDB, Redis.
- Working knowledge: RabbitMQ.
- Also: Next.js, NestJS, Supabase, Stripe, Sentry, AWS, Docker, CI/CD.

## Machine-readable
- https://bhimeshchauhan.github.io/llms.txt
- https://bhimeshchauhan.github.io/resume.json
- https://bhimeshchauhan.github.io/sitemap.xml