Senior Python GenAI Engineer

Kamaleswari

Sr. Python Gen AI Engineer

Email: ***************@*****.*** Phone: +1-405-***-****

PROFESSIONAL SUMMARY

Senior Python GenAI Engineer with 11+ years of experience designing, developing, and deploying enterprise AI, Machine Learning, Generative AI, and cloud-native solutions. Strong expertise in Python, LLM applications, Retrieval-Augmented Generation (RAG), LangChain, LlamaIndex, Hugging Face, PyTorch, TensorFlow, vector databases, embeddings, semantic search, AI assistants, and enterprise knowledge retrieval.

Experienced in designing production-grade AI workflows involving LLM inference, retrieval, orchestration, conversation memory, prompt engineering, model evaluation, document intelligence, and asynchronous processing. Hands-on experience with AWS Bedrock, SageMaker, Lambda, Step Functions, EC2, S3, ECS/ECR, Azure Machine Learning, Azure Data Factory, Docker, Kubernetes, Kafka, Airflow, MLflow, and Redis.

Strong background in scalable distributed systems, REST APIs, FastAPI, microservices, event-driven architectures, data pipelines, vector retrieval, model lifecycle management, production monitoring, and cloud security. Experienced in fine-tuning transformer models using Hugging Face and PyTorch and integrating commercial and open-source foundation models including OpenAI, Amazon Bedrock, and Hugging Face models. Proven experience working in regulated enterprise environments, collaborating across engineering, security, data science, architecture, and business teams, conducting code reviews, mentoring engineers, and establishing reusable AI engineering patterns.

TECHNICAL SKILLS

Programming: Python, SQL, JavaScript, Object-Oriented Programming

Generative AI & LLM: Generative AI, LLMs, Foundation Models, LLM Applications, Prompt Engineering, LangChain, LlamaIndex, Hugging Face, Transformers, OpenAI APIs, Amazon Bedrock, RAG, AI Assistants, Conversation Memory, Question Answering, Summarization, Knowledge Discovery

RAG & AI Retrieval: Retrieval-Augmented Generation, Document Ingestion, Document Processing, Document Classification, Embedding Generation, Vectorization, Semantic Search, Vector Search, Similarity Search, Knowledge Retrieval, Metadata Extraction, Entity Recognition, FAISS, Pinecone

AI Orchestration & Workflows: AI Workflow Orchestration, Inference Orchestration, AWS Step Functions, AWS Lambda, Event-Driven Workflows, Asynchronous Processing, Distributed Processing, Conversation Workflows, Task Orchestration, Streaming Workflows

AI Evaluation & Model Engineering: LLM Evaluation, AI Evaluation, Hallucination Detection, Response Relevance, Retrieval Accuracy, Latency Evaluation, Model Evaluation, Model Monitoring, Model Versioning, Model Lifecycle Management, Model Tuning, Fine-Tuning, PEFT, MLflow

Machine Learning: Supervised Learning, Unsupervised Learning, Deep Learning, Scikit-learn, XGBoost, TensorFlow, PyTorch, Feature Engineering, Hyperparameter Tuning, Cross-Validation

Backend & Distributed Systems: FastAPI, Flask, Django, REST APIs, Microservices, Serverless Architecture, Modular Architecture, JSON APIs, Enterprise API Integration, Distributed Applications, Asynchronous Services

Data Engineering & Streaming: PySpark, Apache Spark, Pandas, NumPy, ETL, Data Ingestion, Data Transformation, Distributed Data Processing, Apache Kafka, Apache Airflow, Redis, Celery

Cloud: AWS, Amazon Bedrock, Amazon SageMaker, EC2, S3, Lambda, Step Functions, ECS, ECR, RDS, IAM, CloudFormation, CloudWatch, Microsoft Azure, Azure Machine Learning, Azure Data Factory

Databases & Storage: PostgreSQL, MySQL, MongoDB, Snowflake, FAISS, Pinecone, Redis

Containers & DevOps: Docker, Kubernetes, Jenkins, Git, SVN, CI/CD, Azure DevOps, Containerized Deployment, Cloud Automation, Infrastructure Automation, Auto Scaling

Security & Observability: IAM, Authentication, Authorization, RBAC, Token Security, Least Privilege, Input Validation, Logging, Monitoring, CloudWatch, Production Support, Debugging, Model Governance, Regulatory Compliance

Architecture & Leadership: Enterprise AI Architecture, Technical Design, Architecture Patterns, Reusable AI Components, API Specifications, Architecture Documentation, Deployment Guides, Code Reviews, Mentoring, Agile Scrum, Cross-functional Collaboration, Technical Workstream Delivery

EXPERIENCE

September 2024 – Present

FINRA, Washington, DC Senior Python Gen AI Engineer

Architected and developed enterprise-scale Generative AI solutions using Python and LLMs for regulatory research, document intelligence, knowledge discovery, and enterprise AI workflows.

Designed production-grade GenAI applications using AWS Bedrock, SageMaker, EC2, S3, Lambda, Step Functions, ECS, and ECR to support scalable AI inference and enterprise workloads.

Designed RAG architectures using LangChain, LlamaIndex, Amazon Bedrock, embeddings, vector search, and enterprise knowledge repositories to deliver context-aware LLM responses.

Developed intelligent AI assistants supporting semantic search, question answering, document summarization, knowledge discovery, and regulatory content generation.

Designed AI workflow orchestration using AWS Lambda and Step Functions for document ingestion, embedding generation, inference orchestration, downstream processing, and asynchronous AI workflows.

Integrated multiple commercial and open-source foundation models using OpenAI APIs, Amazon Bedrock, and Hugging Face Transformers.

Engineered prompt strategies, reusable prompt templates, and conversation memory to improve LLM response quality, contextual relevance, factual accuracy, and user experience.

Built scalable vector retrieval solutions using FAISS and Pinecone to support semantic retrieval across millions of document embeddings.

Developed enterprise FastAPI and REST APIs exposing AI inference and retrieval capabilities to internal applications and business platforms.

Designed reusable Python libraries and modular AI components to standardize GenAI development patterns across multiple projects.

Developed document intelligence pipelines covering ingestion, preprocessing, classification, metadata extraction, entity recognition, summarization, embedding generation, and knowledge retrieval.

Built distributed and event-driven AI processing workflows using Kafka, AWS services, asynchronous processing, Redis, and cloud-native infrastructure.

Fine-tuned transformer-based language models using Hugging Face, PyTorch, and parameter-efficient fine-tuning techniques for domain-specific AI applications.

Implemented LLM evaluation frameworks measuring hallucination rates, response relevance, retrieval accuracy, latency, and production model performance.

Used MLflow for experiment tracking, model versioning, deployment management, lifecycle management, and continuous model improvement.

Optimized inference performance through asynchronous processing, Redis caching, efficient resource utilization, and cloud auto-scaling strategies.

Containerized AI services using Docker and deployed scalable workloads using Kubernetes, Amazon ECS, and Amazon ECR.

Implemented production observability using CloudWatch, application logging, monitoring, debugging, and performance analysis.

Implemented enterprise security controls using AWS IAM, least-privilege access, authentication, authorization, and secure cloud configurations.

Collaborated with data scientists, software engineers, architects, security teams, and business stakeholders to translate business requirements into production AI solutions.

Conducted code reviews, established reusable Python and GenAI engineering practices, and mentored engineers on AI development and production standards.

Produced architecture diagrams, API specifications, deployment guides, governance documentation, and technical design documentation for enterprise AI platforms.

Environment: Python, Generative AI, LLMs, Amazon Bedrock, SageMaker, OpenAI API, Hugging Face Transformers, LangChain, LlamaIndex, RAG, PyTorch, FastAPI, REST APIs, FAISS, Pinecone, MLflow, PySpark, Apache Spark, Pandas, NumPy, Kafka, Redis, AWS Lambda, Step Functions, ECS, ECR, Docker, Kubernetes, AWS, Git, Agile Scrum

May 2022 – August 2024

CVS Health, Woonsocket, RI Python AI/ML Engineer

Designed and developed scalable Python-based AI/ML solutions supporting enterprise healthcare analytics and production decision-support applications.

Developed and deployed machine learning models using Scikit-learn, XGBoost, TensorFlow, and PyTorch for classification, anomaly detection, forecasting, and predictive analytics.

Built scalable data processing pipelines using Pandas, NumPy, PySpark, Spark, Databricks, and Azure Data Factory for large-scale enterprise datasets.

Developed ML lifecycle workflows using MLflow for experiment tracking, model versioning, evaluation, deployment, and monitoring.

Developed FastAPI and Flask REST APIs to expose machine learning inference capabilities to enterprise applications.

Built distributed processing workflows using PySpark, Spark, Kafka, and Databricks to process high-volume and near-real-time enterprise data.

Implemented Airflow orchestration for automated data ingestion, model training, validation, and deployment workflows.

Built reusable data pipelines integrating Snowflake, PostgreSQL, Databricks, and cloud storage services.

Containerized AI/ML applications using Docker and deployed workloads using Kubernetes for scalable production environments.

Implemented CI/CD pipelines using Azure DevOps and Git to automate application and model deployments.

Optimized model performance through feature engineering, hyperparameter tuning, cross-validation, and continuous model evaluation.

Implemented model monitoring, production debugging, root-cause analysis, and performance optimization to maintain production reliability.

Collaborated with data engineers, software engineers, business analysts, architects, and clinical stakeholders to deliver production AI/ML solutions.

Created technical documentation covering ML pipelines, APIs, deployment processes, model governance, and production support.

Environment: Python, Scikit-learn, XGBoost, TensorFlow, PyTorch, MLflow, Pandas, NumPy, PySpark, Apache Spark, Databricks, Azure Machine Learning, Azure Data Factory, Snowflake, PostgreSQL, Apache Airflow, Kafka, Docker, Kubernetes, Azure DevOps, Git, REST APIs, Power BI, Agile Scrum

June 2017 – April 2022

Squad Software Python Developer

Designed and developed scalable enterprise backend applications using Python, Flask, REST APIs, and Object-Oriented Programming.

Developed reusable backend services and REST APIs integrating internal and third-party enterprise systems.

Designed and optimized PostgreSQL and MySQL databases and integrated MongoDB for semi-structured application data.

Implemented asynchronous background processing using Celery and Redis for scheduled and long-running workloads.

Developed secure authentication, authorization, RBAC, and token-based API security.

Developed Python-based data processing and transformation components using Pandas and NumPy.

Developed AWS-based applications using EC2, S3, RDS, Lambda, and CloudWatch.

Built event-driven serverless functions using AWS Lambda for backend automation and processing.

Containerized applications using Docker and automated CI/CD using Jenkins and Git.

Implemented production logging, monitoring, debugging, testing, and performance optimization.

Collaborated with cross-functional engineering teams on architecture, development, testing, deployments, and production support.

Environment: Python, Flask, REST APIs, PostgreSQL, MySQL, MongoDB, Pandas, NumPy, Celery, Redis, AWS EC2, S3, RDS, Lambda, CloudWatch, Docker, Jenkins, Git, JavaScript, SQL, Agile Scrum

June 2013 - July 2015

Zoondia, India Jr. Software Developer

Developed and maintained web applications using Python and Django, implementing reusable modules and business logic for customer-facing and internal enterprise solutions.

Built responsive user interfaces using HTML5, CSS3, JavaScript, jQuery, Bootstrap, and AJAX, improving usability across multiple browsers.

Designed and optimized MySQL database schemas, created SQL queries, stored procedures, and views to support application functionality and reporting requirements.

Assisted in developing RESTful APIs for seamless integration between web applications and backend services using JSON-based communication.

Participated in the complete Software Development Life Cycle (SDLC), including requirement analysis, coding, testing, deployment, and production support.

Implemented server-side validation, session management, authentication, and role-based access control within Django applications.

Performed application debugging, defect resolution, and code optimization to improve application stability and response times.

Wrote unit test cases and supported functional testing to ensure application quality before production releases.

Used Git and SVN for source code version control, branch management, and collaborative software development.

Deployed and maintained applications on Linux (Ubuntu) servers using Apache HTTP Server, monitoring application health and resolving deployment issues.

Worked with JSON and XML data formats for third-party integrations and data exchange between enterprise systems.

Collaborated with senior developers, QA engineers, and business analysts during Agile Scrum sprints to deliver project milestones on schedule.

Documented technical specifications, deployment procedures, and code changes to support ongoing maintenance and knowledge sharing.

Assisted production support teams in troubleshooting application issues and implementing timely fixes while meeting service-level expectations.

Environment: Python, Django, REST APIs, HTML5, CSS3, JavaScript, Bootstrap, jQuery, MySQL, SQL, Git, Linux (Ubuntu), Apache, JSON, XML, Agile Scrum.

Contact this candidate