Sachin Jain

Technical Product Manager

I shape products, design systems, and turn AI into usable experiences.

Technical Product Manager building AI-native products and scalable systems.

Entering system timeline
Experience

A career shaped by systems, and product judgment.

Building across engineering, delivery, and product thinking.

2016 — 2025

UBS

Associate Director · Product Manager & Business Analyst

Led product and platform development for a global swaps processing system, driving the transition from legacy architecture to scalable microservices while enhancing system resilience, operational efficiency, and client-facing capabilities.

ProductBacklog ManagementRequirements ManagementMVP DevelopmentSDLCAgileRelease PlanningEnterprise SystemsCloud ModernizationAI EnablementPlatform ModernizationMicroservices ArchitectureService Fabric
Key Highlights
Owned product roadmap and backlog, aligning trading, operations, and technology stakeholders to deliver scalable platform enhancements
Led migration from legacy systems to a microservices-based architecture on Azure Service Fabric, improving scalability and deployment flexibility
Optimized infrastructure by reconfiguring Service Fabric clusters, reducing server footprint and costs while maintaining system performance
Delivered client-facing solutions that streamlined cash adjustment reporting, significantly improving turnaround times and operational visibility
Designed configurable trading workflows through FIX integration with external vendors, enabling flexible and efficient execution strategies
Championed adoption of Microsoft 365 Copilot within product teams, enabling more efficient requirement drafting and technical documentation
2015 — 2015

Carnegie Mellon University

Capstone Project with Informatica

Six-month capstone project in collaboration with Informatica, focused on designing and building a scalable stream processing framework using Apache Storm, capable of handling high-volume real-time data across constrained environments.

Apache StormStream ProcessingReal-Time SystemsDistributed SystemsData StreamingScalable ArchitecturePerformance OptimizationWindowing TechniquesSystem DesignHigh-Throughput ProcessingClient CollaborationTeam Leadership
Key Highlights
Designed and developed a scalable, configurable stream processing framework using Apache Storm, enabling real-time windowing for data sampling and analysis
Engineered the system to process high-throughput data streams (~2.5GB per minute) with reliable performance and no data loss
Built the framework to operate across Linux environments with significant resource variability (64 KB to 2 GB RAM), ensuring flexibility and efficient execution
Led a three-person team, collaborating directly with the client to define requirements, scope deliverables, and align on implementation
2012 — 2014

Credit Suisse

Post-Trading Platform Developer

Contributed to the development and evolution of trading applications for index and exchange-traded funds, working within service-oriented systems to deliver incremental enhancements aligned with business and regulatory requirements

Trading SystemsETF PlatformsService-Oriented ArchitectureSystem IntegrationSybaseRegulatory SystemsIncremental DeliveryProduction ReleasesFinancial Systems
Key Highlights
Implemented enhancements to trading workflows for index and ETF products, supporting accurate portfolio composition and pricing logic
Developed and integrated service-oriented components connecting C# applications with MS SQL and Sybase, ensuring reliable data flow across system layers
Delivered regulatory-driven changes, including Dodd-Frank requirements, translating complex compliance needs into system behavior
Contributed to structured release cycles across two applications, ensuring incremental features were tested, stable, and production-ready
Shifting from experience to operating model
Chasing AI

Exploring AI Capabilities and How They Fit into Building Products

Hands-on work across retrieval, agents, and workflows to understand what AI can do and how it can be applied in real product experiences.

READY_

What I’ve used

Multi-agent and agent-to-agent systems using Google ADK
Local RAG-based assistants with vector databases for information retrieval
AI coding tools to build end-to-end web applications
Designed prompt-driven workflows with multiple prompts acting as specialized “engineers”
MCP-style integrations to expose and connect agent capabilities
READY_

What I’ve learned

Read more to communicate and explain ideas more clearly
Prompt engineering is less about guardrails and more about directing how the system thinks
AI coding tools burn through context quickly, so decomposition and problem solving still matter
Prompts built from examples can carry hidden bias from the solution they reflect
Multi-agent systems need explicit contracts to coordinate reliably
Context is a limited resource, and how it is curated matters as much as what is included
READY_

What I doing next

Self-directing multi-agent workflow: Creation without human intervention
Context engineering
Exploring how AI systems are deployed: balancing performance, cost, latency, and scale

From system thinking to product execution

The next scene moves from how I operate to what I build.

Selected_Work

A collection of work, ideas, and experiments

Building to understand, evaluate, and apply ideas in real-world contexts.
Testing ideas against real use, beyond theoretical potential.

Rangbheeni

A brand and storytelling website for an NGO that upcycles pre-loved clothes into new products, supports livelihoods for marginalized women, and connects craft with climate-conscious impact.

NGO WebsiteImpact StorytellingCreative DirectionTechnical ConsultingTypeScriptTSX
Upcycle Textile
Climate Justice
Skilled Labor
Women Led

Opportunity

The challenge was to create a website that represented more than products alone. It needed to communicate the NGO’s deeper purpose clearly: upcycling pre-loved clothing, creating dignified work for marginalized women, and linking that work to a broader climate-positive impact story.

Approach

The website introduces the NGO’s mission, showcases its work and products through a fabric-inspired visual language, and guides visitors toward learning more, engaging with the organization, and submitting information through simple integrated form flows.

Highlight

Translated the NGO’s mission into a fabric-led digital identity and interaction system.

Balanced storytelling, social credibility, and lightweight delivery for a small organization.

Used low-cost tooling and hosting decisions to keep the solution practical and maintainable.

Reflection

This project reinforced that good technical decisions are not only about capability, but also about fit. For mission-driven organizations, clarity, affordability, and maintainability can matter more than heavier infrastructure. The work also showed how motion and interface texture can strengthen trust when they are grounded in the organization’s real identity.

Prep Room

Prep Room is an AI-powered interview preparation system designed to help users build clear, structured, and credible answers through guided workflows rather than one-off responses.

AI ProductInterview PreparationTechnical Product ManagementWorkflow DesignSystem ThinkingPrompt Engineering
Coach
Playbook
Highlights
Skills

Opportunity

Interview preparation is usually fragmented across notes, documents, and generic chat threads. That makes answers harder to refine and harder to reuse.

Approach

Users work through answers, save stronger material, and build a structured base of moments and playbooks that can be reused across interview scenarios.

Highlight

Refines interview answers through iterative coaching instead of one-shot generation.

Captures career moments and reusable answer material in one evolving system.

Reduces context switching between notes, chat, and preparation documents.

Reflection

The product became a good test of how AI feels when it is embedded into a workflow instead of acting like a single detached chat box. Contract-based communication improves reliability between agents

Immersive Yatra

AI-powered road trip planner for building detailed multi-day travel plans with structure, flexibility, and practical routing in mind.

AI ApplicationTravel PlanningPrompt EngineeringOpenAI APIStructured OutputsWorkflow Design
Explore

Opportunity

The challenge was to create something that organize routes, timing, and stops into a single flow but leave room for personalization.

Approach

User shares the trip intent and system shall transform it into structured, multi-day planning with more useful pacing, organization, and itinerary detail but still leave a room for user's own customization.

Highlight

Transforms rough travel intent into structured day-by-day planning.

Balances route flow, trip pacing, and richer itinerary detail.

Built as a usable AI product experience, not just a prompt wrapper.

Reflection

AI outputs improve when the prompt aligns with intent rather than over-specifying behavior. Too much constraint reduces usefulness, while the right level of openness improves outcomes.

Personal Research Agent

A focused research assistant designed to synthesize insights across selected papers and material

AI ApplicationResearch AssistantRAGDocument RetrievalContext EngineeringInformation Synthesis
Step_01
Query
Step_02
Retrieve
Step_03
Rank
Step_04
Response

Opportunity

Research material is scattered across multiple papers and it is time-consuming to extract and connect key insights.

Approach

Documents are processed and stored in a FAISS vector database. Relevant sections are identified based on the user query. Retrieved content is processed to generate clear, grounded outputs

Highlight

Supports retrieval, ranking, and synthesis over private source material.

Designed around deeper research workflows rather than simple Q&A.

Represents a stronger AI-systems layer in the portfolio.

Reflection

Chunking strategy and token usage must be balanced — too little context reduces quality, while too much increases cost without better results.

Project Archive
Multi-Agent PM Assistant

Multi-agent assistant concept for product and delivery workflows.

#Agents#Workflow Design#Product Systems
Tweet Sentiment Analyzer

Built a Hadoop MapReduce pipeline on AWS to perform large scale sentiment analysis of twitter data.

#AWS#JAVA#ETL
Skills, stack, and working system
Skills & Tech Wall

Skills, systems, and tools in my stack.

This section combines how you think with what you use, so it grows naturally as your work evolves.

Technical Product Management
Product Strategy
Roadmapping
Backlog Management
Stakeholder Alignment
Agile / Scrum
MVP & Iterative Delivery
Release Planning
APIs (REST)
System Design Awareness
Distributed Systems
Microservices
Data Modeling
SQL (MS SQL, PostgreSQL, MySQL)
Postman
Swagger UI
RAG
Prompt Engineering
Agentic Workflows
Context Engineering
Token Optimization
AI-Assisted Development
Python
C#
Java
FastAPI
Apache Storm
Azure Service Fabric
Visaul Studio
Post-Trade Systems
Trading Systems
FIX Protocol
Prime Services
Client Reporting Systems
Workflow Automation
Agile / Scrum
JIRA
Confluence
MS Project
Visio
Git
Railwayt
Vercel
Cross-Functional Leadership
Technical Product Management
Product Strategy
Roadmapping
Backlog Management
Stakeholder Alignment
Agile / Scrum
MVP & Iterative Delivery
Release Planning
APIs (REST)
System Design Awareness
Distributed Systems
Microservices
Data Modeling
SQL (MS SQL, PostgreSQL, MySQL)
Postman
Swagger UI
RAG
Prompt Engineering
Agentic Workflows
Context Engineering
Token Optimization
AI-Assisted Development
Python
C#
Java
FastAPI
Apache Storm
Azure Service Fabric
Visaul Studio
Post-Trade Systems
Trading Systems
FIX Protocol
Prime Services
Client Reporting Systems
Workflow Automation
Agile / Scrum
JIRA
Confluence
MS Project
Visio
Git
Railwayt
Vercel
Cross-Functional Leadership
Product
Technical Product Management
Product Strategy
Roadmapping
Backlog Management
Stakeholder Alignment
Agile / Scrum
MVP & Iterative Delivery
Release Planning
Technical Fluency
APIs (REST)
System Design Awareness
Distributed Systems
Microservices
Data Modeling
SQL (MS SQL, PostgreSQL, MySQL)
Postman
Swagger UI
AI in Products
RAG
Prompt Engineering
Agentic Workflows
Context Engineering
Token Optimization
AI-Assisted Development
Engineering Context
Python
C#
Java
FastAPI
Apache Storm
Azure Service Fabric
Visaul Studio
Domain & Platform
Post-Trade Systems
Trading Systems
FIX Protocol
Prime Services
Client Reporting Systems
Workflow Automation
Delivery & Collaboration
Agile / Scrum
JIRA
Confluence
MS Project
Visio
Git
Railwayt
Vercel
Cross-Functional Leadership
Continuous learning and public proof
Learning

A continuous view of learning

What I’m learning, in practice and in motion. A mix of certifications, ongoing study, and papers that shape how I think and build.

Certifications

01

5-Day AI Agents Intensive Course with Google

Kaggle
02

Machine Learning Fundamentals and Algorithms

Carnegie Mellon University
03

Deep Learning Specialization by DeepLearning.AI

Coursera
04

Programming for Everybody (Python)

Coursera
05

R Programming

Coursera

Learning Themes

01

Calude - Anthropic

02

Google ADK - agentic development

03

PMP

Read Archive

01

Indoor Navigation using Smartphones: IJEAT, ISSN: 22498958, Volume-1, Issue-5, June 2012

Author
02

Attention Is All You Need

Reading
03

On the Dangers of Stochastic Parrots

To Do
04

Training Language Models to Follow Instructions

InstructGPT
05

Grokking

DeepMind
06

Discovering Latent Knowledge in LLMs

Anthropic

Open for the next build

Contact

See Something, Say Something.

Explore my work, or reach out to connect...

Let’s turn ideas into product.

Open to conversations around product, systems, and AI-driven applications.