Portfolio

The work

Production systems running in global financial workflows. Plus personal projects exploring the frontier of GenAI and LLMOps.

£600K+
Total business value
55
FTEs automated
130K+
Documents processed
5
Markets automated
01

Production work at LSEG

Financial AI systems delivering measurable outcomes in global workflows

GenAI · Production

GenAI Financial Data Extraction Pipeline

£350K+ saved · 50 FTE reduction

Meta-prompting and PydanticAI for extracting structured financial data from broker reports. The accuracy came from deeply understanding the document format — not just the model choice.

LangChainPydanticAIGPT-4Meta-promptingPython
£350K+
Cost savings
50
FTE eliminated
High
Extraction accuracy
RAG · Production

Context-Aware RAG Answer Engine

Source-referenced · Session memory · Analyst-grade

RAG system built specifically for financial analysts. Source-referenced because compliance requires auditability. Session memory because analyst workflows are multi-turn. Prompt design informed by knowing exactly how analysts phrase financial queries.

RAGLangChainVector DBPrompt EngineeringSession Memory
Sourced
Response type
Multi-turn
Memory
Global
User base
Document Intelligence · Production

Korean Regulatory Filing Extraction

15 days → 40 minutes · 130K+ documents · £250K+ saved

End-to-end extraction for Korean financial regulatory filings. 85%+ hit rate across 130K+ documents, 5 FTE reduced. The speed improvement wasn't the hard part — the precision in a non-English financial context was.

PythonNLPCosine SimilarityTwo-stage ClassificationBeautifulSoup
£250K+
Savings
85%+
Hit rate
130K+
Documents
Agentic AI · Research

Multi-Agent Financial Document Intelligence PoC

Executive-endorsed · LangGraph orchestration

Multi-agent PoC for intelligent financial document processing. Designed the agent architecture knowing the document types, the financial context, and the analyst workflows it needed to serve. Earned regional executive endorsement at LSEG.

LangGraphAgentic AILLMFinancial NLPPython
PoC
Stage
Executive
Endorsement
Multi
Agents
Document Intelligence · Production

Image-Based Document Intelligence Pipeline

0% → 64% image coverage · 5 FTE eliminated

Two-stage pipeline: Azure Layout Model for structure extraction + Python rule-based processing for financial semantics. Expanded coverage of image-based financial documents from zero to 64%, opening an entirely new automation surface.

Azure Document IntelligenceAzure Layout ModelPythonRules Engine
0→64%
Coverage gain
5
FTE saved
Two-stage
Architecture
ML · Production

Hybrid ML Ingestion Pipeline

5 markets · 3 FTE saved · 50% scope reduction

Hybrid cosine similarity + two-stage classification pipeline for financial document ingestion across CA, IN, US, AU markets. Rule-based edge cases handled by someone who'd actually seen those edge cases in production financial data.

Cosine SimilarityTwo-stage ClassificationFastAPIHuggingFaceS-BERT
5
Markets
3
FTE saved
50%
Out-of-scope reduced
Recognition

GenAI Leadership Recognition

LSEG · 2023

Multi-agent AI PoC earned regional executive endorsement.

Hall of Fame Award

LSEG · 2023

Recognised for Non-English market automation delivering measurable impact.

Speaker — Learning Forum

LSEG · 2023

Presented on Python problem-solving to the internal engineering community.

Certifications
🎓

PG Programme in Data Science

INSOFE / Carnegie Mellon University

📚

Machine Learning in Production

Andrew Ng · Coursera

🔧

Complete MCP Developer Guide

Udemy

📊

Six Sigma Green Belt

KPMG

Want to build something together?

abhilash.k.panda@gmail.com