Autonomous SDLC platform
A two-pass agent pipeline that classifies Jira tickets, implements fixes, and gates risky changes behind Slack approval — zero manual triage.
8–12 min avg resolution · ~80% token cut
Engineering Manager — AI Systems — Noida, India
Manan Shah
I lead the teams that ship production LLM systems — agent orchestration, cost engineering, and HIPAA-compliant SaaS at scale. 14+ years, hands-on the whole way.
01 — Classify
5–8 turn triage
02 — Gate
Slack human approval
03 — Implement
200-turn autonomous run
04 — Ship
8–12 min avg
// how a Jira ticket becomes a merged PR — the SDLC platform I built at ShyftLabs
14+
years in engineering & product
20+
engineers led at once
6+
AI Platforms Delivered
80%
LLM Cost Reduction
Achievements
Recognition & credentials
Winner — ShyftLabs Hackathon 2026
Built and demoed an autonomous SDLC platform under competitive time constraints,
judged on technical depth, innovation, and delivery.
AWS Certified Advanced Networking – Specialty
Professional Cloud DevOps Engineer (Google)
OntoBAeval: Ontology-Based Automatic Evaluation of Free-Text Response
Towards Improving Automated Evaluation of Java Programs — Springer
My work
Systems I've architected and shipped
Production-grade platforms across US healthcare SaaS, autonomous AI agents, biometric security, FinTech, and TaxTech — all designed for scale, compliance, and measurable outcomes.
AI-SEO pipeline, 300+ sites
An 18-step content DAG generating meta tags, copy, FAQs and schema across 300+ healthcare websites, with multi-model fallback and cost guards.
~72% auto-approval · ~65% cheaper LLM calls
Multi-Tenant Healthcare SaaS — 500+ Sites
Architected a fully isolated multi-tenant SaaS platform hosting 500+ US healthcare websites, each with per-tenant configuration, branding, data isolation, and independent scaling — with zero cross-tenant data leakage.
500+ live tenants · HIPAA compliant · auto-scale per tenant
Booking Management + PIMS Integration
Delivered a HIPAA-compliant Booking Management System with live slot availability sync, real-time PIMS (Practice Information Management System) integration, encrypted PII data handling, and full audit trail — increasing partner adoption by 45%.
45% adoption lift · AES-256 PII · real-time PIMS sync
Adaptive biometric auth
A face authentication platform for SaaS and on-prem deployment, with a biometric model that keeps learning a user's face over time.
Sub-second responses · 30+ languages
TaxTech SaaS, 10M+ records/day
Led end-to-end product strategy for large-scale TaxTech SaaS. Engineered a dynamic tax determination engine with 50+ rule-based algorithms, automating complex TDS computations with 99.9% accuracy.
65% faster normalization · ISO 27001 & GDPR compliant
HIPAA Healthcare Platform
Designed a HIPAA-compliant healthcare product for European startups. Implemented secure patient data exchange and remote consultation features, ensuring strict compliance with health data privacy regulations.
HIPAA Compliant · Secure Patient Data Exchange
AWS High-Traffic Portal & News Engine
Architected a high-traffic news portal on AWS (EC2, S3, RDS, CloudFront) handling 50K+ hits/hour with automated RSS feed ingestion and WordPress-S3 synchronization.
50K+ hits/hour · 80% faster publishing
RBI-compliant mobile banking
Delivered FinTech mobile banking solutions for 165+ cooperative banks using C# and Flutter, ensuring 99.99% uptime and 1M+ secure transactions/month per bank.
165+ banks · 1M+ txns/month per bank
Mobile wallet platform
Launched a scalable mobile wallet with 100K+ active users, integrated BillDesk payment gateway, enabling instant UPI and bill payments with <2 sec transaction latency.
100K+ users · <2 sec latency
World Bank air quality monitoring
Partnered with World Bank on geofencing and NO₂ emission monitoring, leveraging Python, PostgreSQL, and geospatial analytics for real-time air quality visualization.
Geofencing · real-time visualization
Unified mobile banking app
Co-founded and built a unified mobile banking app in Java, enabling 70+ banks to perform secure, real-time view-only operations — reducing support load by 40%.
70+ banks · 40% less support load
What I do
Four things I'm actually good at
AI
AI Systems
LLM pipelines, agent orchestration, cost & token engineering, RAG, multi-model fallback.
EM
Team Leadership
Leading 10–20+ engineers through delivery, hiring, and agile execution.
CLOUD
Cloud Architecture
AWS-native, multi-tenant SaaS, microservices, high-concurrency systems.
PROD
Product Delivery
Turning business goals into shipped roadmaps — on time, at 98%+ delivery rates.
Experience
Where I've built this
Jun 2025 — Present
Engineering Manager
ShyftLabs Pvt. Ltd. · Noida
- Architected an autonomous SDLC orchestration platform unifying Jira, Claude Code, Slack, and GitHub via a two-pass pipeline, auto-resolving tickets in 8–12 min average with zero manual triage.
- Built an isolated multi-repo Git worktree framework enabling 3+ concurrent repo branches without collision, gated by Slack human-in-the-loop approval.
- Engineered self-improving agent memory architecture with token-efficient context engineering, cutting redundant token spend by ~80%.
- Built an AI-SEO overlay pipeline (15 content keys/page) across 300+ healthcare websites using AWS Bedrock, BullMQ, MongoDB, and Redis, achieving ~72% auto-approval and cutting full-price LLM calls by ~65%.
- Led zero-data-loss migration of 500+ production domains; delivered HIPAA-compliant Booking Management System increasing partner adoption by 45%.
- Co-developed shared OAuth2/SSO/MFA security libraries, cutting integration overhead in half across all subsequent platform spin-offs.
Apr 2024 — Jun 2025
Engineering Manager
Conevet Technologies Pvt. Ltd. · Ahmedabad
- Architected an enterprise-grade face authentication platform (FastAPI) supporting SaaS and on-premise deployment with hardware-locked licensing, achieving sub-second API responses across 30+ languages.
- Designed a self-improving adaptive biometric engine that continuously updates face embeddings without re-enrollment, secured with post-quantum cryptography, liveness detection, and dynamic JWT lifecycles.
- Designed and deployed a scalable algorithmic trading system leveraging smart money concepts with real-time multi-asset market data analysis.
Jan 2022 — Mar 2024
Associate Director — Tax Technology
BDO in India · Ahmedabad
- Led end-to-end product strategy and architecture for large-scale TaxTech SaaS solutions leveraging microservices and API-first design.
- Engineered a dynamic tax determination engine (Laravel, Python) with 50+ rule-based algorithms, automating complex TDS computations with 99.9% accuracy.
- Built high-throughput data processes processing 10M+ financial records/day using NumPy vectorization, achieving 65% faster data normalization.
- Architected secure workflows implementing AES-256 encryption and role-based access control, ensuring 100% compliance (ISO 27001, GDPR).
- Led a 20+ member hybrid team (engineering, QA, design, DevOps) through full agile lifecycles, improving velocity by 40% and reducing blockers by 30%.
- Acted as hands-on technical product owner, contributing clean, test-driven code and ensuring high sprint deliverable compliance with quality and performance KPIs.
- Spearheaded Angular component library development, standardizing UI/UX across multiple platforms, delivering 30% faster dev cycles and 50% reduction in UI defects.
Mar 2016 — Dec 2021
Vice President — Tech Development
TM Systems Pvt. Ltd. · Ahmedabad
- Delivered RBI-compliant FinTech mobile banking solutions for 165+ cooperative banks using C# (backend) and Flutter (frontend), ensuring 99.99% uptime and 1M+ secure transactions/month per bank.
- Launched a scalable mobile wallet platform with 100K+ active users and BillDesk payment gateway integration, enabling instant UPI and bill payments with <2 sec latency.
- Architected and deployed a high-traffic news portal on AWS (EC2, S3, RDS, CloudFront) handling 50K+ hits/hour with automated RSS ingestion, achieving an 80% reduction in content publishing time.
- Developed RESTful API-based enterprise portal for MBC Group (UAE) with multi-role workflows, secure payment gateway integration, and auto-scaling backend, improving operational efficiency by 40%.
- Led end-to-end product development of Club Management, University ERP, and Custom Accounting Solutions, standardizing codebase and reducing time-to-market by 35%.
- Collaborated with European healthcare startups to design HIPAA-compliant health products with secure patient data exchange and remote consultation features.
- Partnered with World Bank on geofencing and NO₂ emission monitoring project, leveraging Python, PostgreSQL, and geospatial analytics for real-time air quality visualization.
Jun 2012 — Feb 2016
Co-Founder
Manastr · Ahmedabad
- Developed unified mobile banking app using Java, enabling 70+ banks to perform secure, real-time view-only operations, improving customer access and reducing support load by 40%.
- Delivered "UR Invited" – multi-event and invitation management app built on MVC architecture, supporting 10K+ concurrent users with RSVP tracking and push notifications.
- Engineered fast-delivery and vendor management platform using CodeIgniter (PHP) with live location tracking, order routing, and performance analytics, cutting turnaround time by 45%.
- Oversaw full SDLC operations from system analysis, database design, and code review to production deployment, ensuring bug-free releases.
- Maintained strong client relationships through transparent communication, consistent progress reporting, and milestone delivery adherence, driving long-term client retention.
About
Manager first by title. Builder first by habit.
What kind of problems I take on
I gravitate toward systems where the constraints are real — regulatory (HIPAA, ISO 27001, GDPR, RBI), operational (300+ tenants, 10M+ records a day), or architectural (agents that have to be trusted with production code). The common thread has been owning it end to end: architecture, team, and delivery.
Hands-on vs. managing
As an Engineering Manager I'm accountable for a roadmap and a team of 10–20+ people, but I still design the systems and write meaningful amounts of code — the SDLC agent pipeline, the biometric matching engine, and the tax rule engine were all things I architected personally.
My take on AI in production
Most interesting problems aren't about the model — they're about cost, safety, and control. Bounded agent turns, Slack approval gates, multi-layer caching, and per-tenant cost guards. I'd rather ship a system that's slightly less magical and fully explainable than one that's impressive in a demo and unaccountable in production.
Contact
Let's talk
Open to engineering leadership roles, AI advisory, and conversations about production LLM systems.
Based in Noida, India · open to remote & relocation conversations