General Information
- Full Name
-
Sunil Sarolkar
- Role
-
Principal Solution Architect (AI & GenAI Toolchain)
- Location
-
Pune, India
- Languages
-
English, Hindi, Marathi
- Focus
-
GenAI & Financial Services / Insurance
Summary
AI architecture leader with 16+ years designing and deploying enterprise-scale solutions for Financial Services. Deep BFSI domain expertise across capital markets, derivatives and regulatory reporting, paired with proven strength architecting GenAI and agentic systems (LangGraph, LangChain, Vertex AI) that bridge cutting-edge AI with legacy banking data. Trusted technical authority in customer-facing and executive-advisory roles, translating complex business requirements into secure, scalable, cloud-native architectures.
16+ years in BFSI — Capital Markets & Derivatives (CDS/IRS, Dodd-Frank) · Regulatory Reporting · Corporate Cashflow · Credit Bureau / Microfinance · Middle & Back-Office Banking — at Deutsche Bank, Credit Suisse via Cognizant & HSBC.
Professional Experience
June 2026 – Present
Principal Solution Architect, Customer Facing
US Insurance Client via Zensar Technologies, Pune
-
Agent-Assist Next Best Offer Engine (Insurance): Architected a recommendation engine combining a Neo4j persona knowledge graph with lifetime-value, likelihood-to-act and product-fit models — served from AKS via Helm with Azure Blob-backed model artifacts.
-
Legacy Modernization — COBOL/Tandem to .NET on Azure: Leading discovery and phased migration strategy for a mainframe-to-cloud program — AST-driven transformation pipeline, spec-driven development with AI coding agents, and golden-master validation to guarantee functional equivalence.
Jul 2015 – May 2026
Assistant Vice President, Engineering Lead
Deutsche Bank, Pune
-
Executive Advisory & Technical Presales (BFSI): Primary AI technical architect for global BFSI business lines — led design workshops and presented GenAI ROI and architecture strategy directly to executive leadership.
-
Prioritization Rubrics across Business Units: Built and executed a standardized evaluation rubric to prioritize architecture requirements across multiple business units in parallel, matching recommendations to each unit’s engineering maturity and business velocity.
-
Enterprise-Scale RAG — DB Omni: Implemented an organisation-wide RAG pipeline integrating GitHub, Bitbucket and Confluence into a single unified search; enabled code explainability with business context and surfaced knowledge gaps — materially reduced information-search time.
-
Agentic QA & Reconciliation Automation: Architected an enterprise multi-agent system (LangGraph, LangChain) automating end-to-end test execution and post-trade data reconciliation across banking platforms — QA testing cycles reduced by ~60%.
-
Corporate Cashflow Analytics — Deterministic ML at Scale: Implemented agentic workflow using deterministic tool calls and a custom-trained model with confidence scoring; low-confidence cases route to human review, feeding continuous retraining. Processes 10B+ monthly records — ~70% reduction in compliance rule-change effort, ~30% performance improvement.
-
Regulatory Data-Adjustment Automation: Automated manual data adjustments in the back-office regulatory reporting warehouse (event-driven architecture on GCP — BigQuery, Dataflow — and AWS), reducing Functional Analyst adjustment effort by ~70%.
-
Enterprise LLMOps: Established distributed tracing and audit logging so every automated financial decision is traceable; designed functional evaluation metrics for real-time model and agent quality.
Dec 2013 – Jul 2015
Software Engineer
Credit Suisse via Cognizant Technology Solutions
-
Back-Office Position Management (Capital Markets): Built core backend for an enterprise transactional Data Warehouse managing real-time account-position changes across global securities infrastructures; used ESB to handle high-frequency capital-markets data.
Aug 2011 – Dec 2013
Software Engineer
HSBC Software Development India
-
Dodd-Frank Compliance & Derivatives Processing: Engineered middle-office integration platforms handling FIXML APIs for DTCC and MarkitWire to process Credit Default Swaps (CDS) and Interest Rate Swaps (IRS) trade data for Dodd-Frank regulatory reporting.
-
Trading Platform Integrations: Built secure, low-latency “Smart Client Frameworks” to route real-time transaction data from Bloomberg front-office terminals downstream into Global Calypso back-office systems for post-trade clearing and settlement.
Mar 2010 – Aug 2011
Software Engineer
High Mark Credit Information Services (now CRIF High Mark)
-
Credit Bureau Bulk Ingestion (Consumer Credit / Fintech): Designed high-volume, secure ETL pipelines ingesting bulk financial data from Micro-Finance Institutions; automated cleansing and transformation into regulator-mandated formats for credit-bureau reporting.
Core Competencies
BFSI Domain Expertise
- Capital Markets & Derivatives (CDS, IRS, FIXML)
- Dodd-Frank & Regulatory Reporting
- Corporate Cashflow
- Credit Bureau / Microfinance
- Middle & Back-Office Operations
- Financial Data Warehousing
Customer Engineering & Advisory
- Technical Discovery
- Architectural Scoping
- Rapid Prototyping & PoC Delivery
- Executive Presales
- Value-Realization Mapping
- Cross-Functional Stakeholder Alignment
Agentic AI & Search Engineering
- LangGraph
- LangChain
- Vertex AI
- Production RAG Pipelines
- Text-to-SQL
- Semantic & Hybrid Retrieval
- Evaluation (LLM-as-a-judge)
Enterprise Integration & API Governance
- Model Context Protocol (MCP)
- OpenAPI
- API Gateways
- ESB
- Event-Driven Architectures
- Distributed Systems
Data Engineering & Pipelines
- Kafka
- Spark
- Airflow
- BigQuery
- Dataflow
- Streaming & Batch Processing
Security, Observability & Cloud
- OAuth2
- Short-Lived Credential Management
- Distributed Tracing
- Audit Logging
- Blast-Radius Containment
- Cloud-Native Design (GCP, AWS)
Technologies & Tools
Languages
- Java
- Python
- C++
- HTML/CSS
- SQL
Frameworks & Libraries
- Spring Boot
- PyTorch
- Keras
- LangChain
- Transformers
- LangGraph
Cloud & DevOps
- Google Cloud
- Docker
- Microservices
- Distributed Systems
- Azure
- AWS
- Kubernetes
- Helm
AI / ML
- Generative AI
- Computer Vision
- Predictive Maintenance
- NLP
- Vertex AI
- Retrieval-Augmented Generation (RAG)
- Text-to-SQL
- Model & Agent Evaluation
Data Engineering & Integration
- Kafka
- Spark
- Airflow
- BigQuery
- Dataflow
- Model Context Protocol (MCP)
- OpenAPI
- Event-Driven Architectures
Key Projects
Trade Data Insights Pipeline
Corporate Cashflow, Deutsche Bank (enterprise multi-agent workflow)
-
Led technical discovery and scoping to ingest and process unstructured corporate cashflow telemetry; translated vague business requests into a concrete multi-agent architecture (LangChain) reasoning over complex financial data. ~70% reduction in compliance rule-change effort, ~30% performance improvement.
-
Applied Model Context Protocol (MCP) principles for safe agent-to-database interaction, with evaluation guardrails ensuring deterministic outputs for compliance review.
Structformer — Regulatory Data Text-to-SQL Engine
Deutsche Bank regulatory reporting
-
Designed a custom Transformer engine (SentencePiece tokenizer) automating data adjustments for financial regulatory reports. ~70% time saved in data adjustment.
-
Built automated Text-to-SQL workflows letting non-technical compliance stakeholders query complex data lakes securely; validated against deterministic financial-accuracy metrics (99%).
AI-Driven Indian Sign Language Translation
IISc Capstone
-
Real-time, low-latency multimodal ML pipeline for continuous streaming under strict edge constraints; custom temporal recognition (OpenPose + Transformer/LSTM) delivering high-speed inference without heavy cloud compute.
Education
2024
PG Certification, Computational Data Science
IISc Bangalore
-
Grade A+ (94%; 100% in Scalable Computing & 90% in ML). Top Talent Pass (TTPS) Eligible.
Professional Machine Learning Engineer
Google Cloud
2024
Professional Data Engineer
Google Cloud
-
Demonstrated proficiency in designing and building data processing systems and operationalizing machine learning models on Google Cloud.
Associate Cloud Engineer
Google Cloud
2007
Diploma in Advanced Computing
C-DAC / ACTS, Pune
2006
B.E. Electronics
Pune University, VIT College
Certifications & Badges
Training & recognition
Learning badges from Credly
20 public credentials and learning badges.

Derive Insights from BigQuery Data Skill Badge

Build a Data Mesh with Dataplex Skill Badge

Build a Data Warehouse with BigQuery Skill Badge

Explore Generative AI with the Vertex AI Gemini API Skill Badge

Inspect Rich Documents with Gemini Multimodality and Multimodal RAG Skill Badge
Develop GenAI Apps with Gemini and Streamlit Skill Badge

Prompt Design in Vertex AI Skill Badge

Build and Deploy Machine Learning Solutions on Vertex AI Skill Badge

Engineer Data for Predictive Modeling with BigQuery ML Skill Badge

Classify Images with TensorFlow on Google Cloud

Build a Secure Google Cloud Network Skill Badge

Build Infrastructure with Terraform on Google Cloud Skill Badge

Deploy Kubernetes Applications on Google Cloud Skill Badge

Develop Your Google Cloud Network Skill Badge

Implement Cloud Security Fundamentals on Google Cloud Skill Badge

Implement Load Balancing on Compute Engine Skill Badge

Prepare Data for ML APIs on Google Cloud Skill Badge

Set Up an App Dev Environment on Google Cloud Skill Badge

Google Cloud Certified - Professional Machine Learning Engineer

Google Cloud Certified - Associate Cloud Engineer
Each badge links to its public credential record.
Honors and Awards
2022
-
Deutsche Bank Excellence Award: Recognized for outstanding contribution to Cloud Migration initiatives.
2018
-
Deutsche Bank Excellence Award: Awarded for delivery excellence in the Accounting Subledger project.
2012
-
GBM, AMG & GBP Awards (HSBC): For exceptional delivery and crisis support.
Interests
Professional: GenAI & LLMs, Distributed Systems Architecture, Astrophysics, Quantum Computing.
Personal: Trekking (Himalayas), Chess Strategy, Yoga & Mindfulness.