Skip to content

Polam Srija

Software Engineer, AI/ML Systems • United States • p************@gmail.com • 848****467 • drivetube.ai/•••••

Professional Summary

AI/ML Engineer with 3+ years of experience building and operating production ML systems for financial services and enterprise AI platforms. Strong track record designing feature engineering frameworks and low-latency inference pipelines using Python, scikit-learn, XGBoost, Kafka, Spark, and Google Cloud (Vertex AI, BigQuery, Dataflow). Experienced developing retrieval-augmented generation (RAG) solutions using FAISS and Redis and deploying them with MLflow and Terraform in CI/CD-driven environments. Delivered fraud detection, portfolio-allocation, and document-processing solutions that improved operational effectiveness and model reliability. I own model lifecycle automation, observability, and reproducible experiment pipelines to ensure safe, scalable model serving in production.

Technical Skills

Programming Language: Python,SQL
Backend Technologies: FastAPI
Databases: Redis
DevOps & Infrastructure: Terraform,Docker
Messaging & Monitoring: Apache Kafka
Data Engineering & Processing: Apache Spark
Data Analysis & Visualization: Streamlit,Power BI
Machine Learning & AI: SHAP,SMOTE
AI/ML Frameworks & Libraries: scikit-learn,XGBoost,Optuna,Hugging Face,Datasets
Vector Databases & RAG: FAISS,Retrieval-Augmented Generation,RAG,BM25,HNSW
MLOps: MLflow
Data Integration & ETL: Google Cloud Dataflow

Work Experience

FIDELITY INVESTMENTS
TX, USA
AI/ML Engineer
Apr 2025 – Present
Worked at Fidelity Investments supporting production ML and retrieval systems for portfolio analytics, trading decision-support, and enterprise reporting in the financial services domain.
Tech Stack: XGBoost, scikit-learn, Kafka, Google Dataflow, BigQuery, FAISS, Redis, Vertex AI, HNSW, BM25, MLflow, Terraform
  • Built and launched production ML systems for real-time analytics and decision-making, improving operational efficiency and outcomes for 500+ users.
  • Developed predictive portfolio-allocation models using XGBoost and scikit-learn to generate risk-aware recommendations for production trading pipelines.
  • Engineered scalable data ingestion pipelines using Kafka and Google Dataflow to reliably stream events into downstream processing.
  • Optimized feature storage and analytics in BigQuery to accelerate model training and reporting for portfolio analytics workloads.
  • Designed a feature-engineering framework for time-series financial data to produce standardized features and cross-sector risk indicators for ML and LLM-based components.
  • Implemented a retrieval-augmented generation (RAG) pipeline using FAISS and Redis to index embeddings for semantic search and retrieval.
  • Deployed the RAG service on Vertex AI Search and tuned HNSW/BM25 ranking to improve retrieval relevance by 35%.
  • Established MLOps pipelines with MLflow and Terraform to enable automated retraining, reproducible experiments, and production-grade deployments.
Capgemini
India
AI/ML Engineer
Jan 2022 – Apr 2024
Delivered ML and NLP solutions for financial-services clients, focusing on fraud detection, document processing, and real-time inference as part of consulting engagements.
Tech Stack: scikit-learn, SMOTE, Apache Spark, Docker, FastAPI, Optuna, SHAP, Power BI
  • Developed fraud-detection models using scikit-learn with SMOTE to address class imbalance across datasets from 5+ financial institutions.
  • Refined classification pipelines and integrated financial KPIs to improve recall and operational robustness for risk scoring.
  • Built large-scale NLP document-processing pipelines on Apache Spark to extract structured features and reduce manual review time.
  • Deployed containerized ML services with Docker and FastAPI, reducing deployment time by 38% through automated builds and rollout controls.
  • Accelerated hyperparameter tuning using Optuna to improve convergence and overall model performance for classification tasks.
  • Visualized explainability outputs with SHAP and Power BI to support investigation workflows and stakeholder decision-making.

Projects

FSDD - Spoken Digit Classifier
Tools Used: Hugging Face Datasets, Streamlit, joblib, scikit-learn, LogisticRegression, MFCC
  • Achieved 94.1% test accuracy on the Free-Spoken Digit Dataset using a stratified 70/15/15 split and fixed seed; produced confusion matrix and per-class metrics.
  • Designed a portable data-loading pipeline with Hugging Face Datasets and an automatic fallback to the official FSDD ZIP for cross-platform compatibility.
  • Built an audio preprocessing pipeline including resampling to 8 kHz, mono conversion, padding/trimming to 1s, normalization, and MFCC extraction for consistent inputs.
  • Developed a browser-based Streamlit app with upload and recording capabilities to enable real-time predictions with low CPU latency.
  • Packaged the pipeline into a lightweight joblib artifact (StandardScaler → LogisticRegression) to simplify versioning and deployment.

Education

University of North Carolina at Charlotte
Master of Science in Computer Science • Charlotte, North Carolina • Aug 2024 – Dec 2025

Powered by Drivetube · Create your own profile at drivetube.ai

Explore Drivetube

  • Drivetube Profile — your free digital resume — at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept. Documentation.
  • Free Job Board — verified openings crawled ATS-by-ATS from 100,000+ real company career pages across 35 ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed. Documentation.
  • Job Hunt Program — managed job hunting, a one-time purchase from $199.99. JobScout matches verified roles to your real experience band, Blend AI writes a uniquely tailored resume and cover letter for every application, and the Autofill extension fills the form — or Let Us Apply submits it for you. Documentation.
  • Resume Writing Services — human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile. Documentation.
  • Community Membership — from $4.99/month (₹1,999/year in India). Unlocks the gated job-board filters — visa sponsorship, security clearance, workplace and application time — plus Job-Scout AI matching, Resume Report AI, Interview AI prep sheets, Recruiter Outreach AI sent from your own Gmail, Apply or Skip triage, a daily market feed and a $10,000+ library including 23 ATS-validated resume templates. Documentation.
  • Drivetube Hire — for employers — hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do. Documentation.

Full product documentation — every product explained, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.

The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.