Headline

Software Engineer @ Capgemini | Data Engineering & AI Automation

About

As a Software Engineer at Capgemini, I work at the intersection of data engineering, ETL automation, and AI-driven pipelines — helping teams move from raw, messy data to decisions they can trust. My stack: → Data Engineering: Informatica, dimensional modelling, star/snowflake schemas, ETL pipelines → Automation & AI: n8n workflows, Generative AI integration (Langchain), intelligent orchestration → Cloud & Infra: Microsoft Azure, SQL Server, Linux → Languages: Java (DSA · 1000+ LeetCode), Python (ML), Node.js What I care about: building backends and pipelines that are fault-tolerant, observable, and actually maintainable by the team that inherits them. Before Capgemini, I attended Amazon's ML Summer School — covering deep neural networks, supervised learning, and probabilistic graphical models alongside engineers from across India. I'm actively targeting SDE roles at Fintech companies, FAANG, and high-growth startups where data and backend engineering sit at the core of the product — not as an afterthought. If you're building something ambitious and need someone who brings both strong fundamentals and a bias for getting things shipped — let's talk. 📩 b3sutradhar@gmail.com | Open to: Full-time SDE roles · Data Engineering · Backend Engineering

Location

Hyderabad

AI stack

antigravity

claude code

claude

cursor

deepseek

gemini

Work experience

Software Engineer at Capgemini, Jul 2025 - Present · 1 yr 4 mos, Bengaluru, Karnataka, India, → Architected an AI-powered Knowledge & Triage Agent (Python, LangChain, FAISS) featuring a semantic vector matching engine. This automated error classification beyond exact string matches, significantly reducing support ticket escalations across high-volume weekly error events. → Built a self-learning knowledge retrieval pipeline integrating NVIDIA NIM embeddings and SQL Server execution logs. This enabled continuous, automated knowledge base updates from compiler workflows and drastically improved retrieval efficiency for daily log lookups. → Developed secure enterprise RESTful APIs (FastAPI, X-API-KEY) connecting internal applications to AI-driven triage services. Delivered these automation features iteratively within an Agile/Scrum team, utilizing Azure Pipelines for streamlined CI/CD.

Software Engineer Trainee at Capgemini, Jul 2025 - Aug 2025 · 2 mos, Bengaluru, Karnataka, India, → Designed and implemented ETL pipelines using Informatica, processing structured data across dimensional models (star and snowflake schemas) — reducing manual validation effort for the data team. → Validated end-to-end data flow from source to target across multiple warehouse layers, ensuring zero data-integrity failures during migration testing cycles. → Contributed to Data Warehouse architecture decisions — applying dimensional modelling principles to optimize query performance and downstream reporting reliability

Trainee at Amazon, Sep 2023 - Oct 2023 · 2 mos, Bengaluru, Karnataka, India, → Selected for Amazon's ML Summer School (India) — a competitive program covering deep neural networks, supervised learning, and probabilistic graphical models across 8 modules in 4 weeks. → Applied probabilistic graphical model concepts to personal ML projects in Python, strengthening foundation for subsequent generative AI certifications. → One of a limited cohort of students across India accepted into the program, competing alongside engineering students from top-tier institutions.

Education

Bachelor of Technology - BTech, Computer Science, KIIT - Kalinga Institute of Industrial Technology

12th Physics Chemistry Mathematics English Computer Science, Delhi Public School - India

Public links

github: https://github.com/Bikram2473

leetcode: https://leetcode.com/bikramsutradhar