AI/ML Automation Engineer

SAI NIKHIL P

Senior AI/ML Engineer LLM, RAG & NLP MLOps & LLMOps API & Cloud Architect

************@*****.*** 469-***-****

SUMMARY:

AI/ML Engineer with 11+ years of experience, including 5+ years in Artificial Intelligence, Machine Learning, NLP, and Generative AI. Specialized in building production-grade LLM applications, Retrieval-Augmented Generation (RAG) systems, and intelligent text analytics solutions using Python.

Strong hands-on experience in API development, vector databases, prompt engineering, LLM evaluation, and scalable deployment of AI systems. Proven expertise in building end-to-end AI pipelines including data ingestion, embedding generation, semantic search, and model serving.

Experienced in MLOps and LLMOps practices including model monitoring, evaluation, CI/CD, versioning, and deployment using tools like LangSmith, MLflow, and Kubernetes-based architectures. Skilled in working with AWS, Azure, and GCP cloud platforms.

.

KEY HIGHLIGHTS:

•Designed and deployed enterprise Generative AI solutions using AWS Bedrock, Amazon SageMaker, Anthropic Claude, GPT-4o, Amazon Nova, Llama, and Mistral foundation models.

•Built production-grade Retrieval-Augmented Generation (RAG) systems using Pinecone, Weaviate, ChromaDB, OpenSearch Vector Engine, FAISS, and hybrid search architectures.

•Developed autonomous Agentic AI systems and multi-agent orchestration frameworks using LangChain, LangGraph, CrewAI, MCP, and LlamaIndex.

•Developed NLP-based text analytics and document intelligence solutions for large-scale enterprise datasets.

•Built and deployed RESTful APIs for AI/ML services using FastAPI and Flask.

•Implemented LLM evaluation frameworks using LangSmith, Ragas, and DeepEval for performance monitoring.

•Designed and integrated LLM guardrails and safety layers for secure and reliable AI outputs.

•Experience working with LLM orchestration and proxy frameworks such as LiteLLM.

•Implemented CI/CD pipelines, model versioning, and deployment strategies for ML and LLM systems.

•Built scalable AI deployment pipelines using Docker, Kubernetes, GitHub Actions, Terraform, CI/CD, and MLOps frameworks.

•Delivered production AI platforms within Financial Services and Healthcare domains while ensuring security, compliance, observability, and scalability.

TECHNICAL SKILLS:

Languages

Python, SQL, R, Java, JS/TS, C#, MATLAB, JavaScript

Generative AI & LLMs

AWS Bedrock, Amazon SageMaker, OpenAI GPT-4o, Anthropic Claude, Amazon Nova, Llama, Mistral, Hugging Face Transformers, Prompt Engineering, Fine-Tuning, LoRA, QLoRA, PEFT, Model Evaluation, AI Guardrails

RAG & Retrieval

Retrieval-Augmented Generation (RAG), Semantic Search, Hybrid Search, Embeddings, Vector Search, Knowledge Retrieval, Document Intelligence

Agentic AI & Orchestration

LangChain, LangGraph, CrewAI, LlamaIndex, MCP, Multi-Agent Systems, Autonomous AI Agents, Agent Orchestration, Tool Calling, Memory Management, Planning Agents

Libraries/Frameworks

PyTorch, TensorFlow, Scikit-learn, Hugging Face, spaCy, NLTK

Vector DBs

Pinecone, Weaviate, ChromaDB, OpenSearch Vector Engine, FAISS, Milvus

Backend & APIs

FastAPI, Flask, REST APIs, GraphQL, API Gateway, WebSockets, Server-Sent Events (SSE)

AWS Cloud

AWS Bedrock, SageMaker, Lambda, API Gateway, ECS, EKS, EC2, S3, DynamoDB, CloudWatch, IAM

Databases

SQL Server, Oracle, MySQL, PostgreSQL, MongoDB, DynamoDB, Teradata, NoSQL Databases

Data Engineering

ETL Pipelines, Data Modeling, Data Lakes, Spark, PySpark, Hadoop, Kafka, Data Warehousing

MLOps & Tools

Docker, Kubernetes, GitHub Actions, Terraform, MLflow, Kubeflow, Airflow, LangSmith, Weights & Biases, CI/CD Pipelines, Model Monitoring, AI Governance, Model Versioning

Security & Observability

CloudWatch, LangSmith, Fiddler AI, AgentOps, Logging, Monitoring, IAM, PII Protection, Governance, Compliance

Data Science & NLP

PyTorch, TensorFlow, Scikit-learn, XGBoost, LightGBM, NLP, Statistical Modeling, Predictive Analytics, Explainable AI

Knowledge Technologies

Knowledge Graphs, Semantic Search, Metadata Management, Enterprise Search

CERTIFICATIONS

•Microsoft Certified: Azure AI Engineer

•AWS Certified Machine Learning

PROFESSIONAL EXPERIENCE:

Client: Charles Schwab, Westlake, TX March 2023 – Till Date

Role: AI/ML Automation Engineer

Project: Designed and deployed AI applications for financial analytics, chatbot automation, and real-time decision support for trade surveillance and market risk monitoring.

Responsibilities:

•Architected and developed end-to-end LLM-powered applications for trade surveillance, compliance automation, and financial risk analytics using Python.

•Designed and deployed enterprise Generative AI applications using AWS Bedrock, Amazon SageMaker, Anthropic Claude, OpenAI GPT-4o, and Amazon Nova foundation models for financial advisory and compliance automation use cases.

•Built intelligent document processing and financial knowledge retrieval platforms using RAG architectures, vector search, and agentic AI orchestration frameworks.

•Designed vector search architectures using Pinecone, Weaviate, OpenSearch Vector Engine, ChromaDB, and FAISS supporting semantic retrieval across large-scale financial datasets.

•Developed NLP-driven text analytics solutions for financial documents including classification, summarization, and entity extraction.

•Implemented CI/CD pipelines for AI services using GitHub Actions and Docker-based deployments.

•Built autonomous AI agents and multi-agent collaboration frameworks for portfolio analysis, compliance validation, financial document review, and advisor assistance workflows.

•Integrated AI systems with backend services, REST APIs, and enterprise data platforms for real-time decision-making.

•Established LLM evaluation frameworks measuring accuracy, latency, reliability, and cost optimization using Ragas, DeepEval, and LangSmith.

•Integrated guardrails and safety frameworks to mitigate hallucinations and ensure reliable AI outputs.

•Developed scalable and distributed AI architectures using FastAPI, Docker, Kubernetes, and cloud-native services.

•Implemented real-time AI inference pipelines using streaming APIs, WebSockets, and async processing.

•Automated prompt engineering, embedding optimization, and hybrid retrieval strategies to improve response quality.

•BuBuilt LLM evaluation pipelines using LangSmith, Ragas, and DeepEval to measure response quality and accuracy.

•Developed cloud-native AI services using AWS Lambda, API Gateway, ECS/EKS, S3, DynamoDB, CloudWatch, and IAM for secure enterprise deployment.

•Implemented LLM proxy and orchestration using LiteLLM for multi-model routing and cost optimization.

•Deployed production-grade AI solutions serving thousands of users with observability, monitoring, governance, auditability, and compliance controls.

•Collaborated with cross-functional teams including data engineering, DevOps, and business stakeholders to deliver enterprise AI solutions.

Technologies: Python, AWS Bedrock, Amazon SageMaker, AWS Lambda, API Gateway, ECS, EKS, S3, DynamoDB, CloudWatch, IAM, LangChain, LangGraph, CrewAI, MCP, LlamaIndex, GPT-4o, Anthropic Claude, Amazon Nova, Llama, Mistral, Pinecone, Weaviate, ChromaDB, OpenSearch Vector Engine, FAISS, Milvus, LangSmith, AgentOps, Ragas, DeepEval, Fiddler AI, FastAPI, Docker, Kubernetes, Terraform, GitHub Actions, MLflow, Databricks, Snowflake, PySpark, Tableau, Power BI, LoRA, QLoRA, PEFT

SCL Health, Denver, CO June 2019 – February 2023

MLOps / LLMOps Developer

Project: Developed generative AI tools and agents to automate the analysis, summarization, and visualization of telehealth and patient data.

Responsibilities:

• Automated end-to-end MLOps workflows for healthcare AI systems using MLflow, Databricks, Azure, and AWS.

•Built automated AI model training, deployment, monitoring, drift detection, and retraining pipelines for clinical analytics applications.

•Developed LLM-powered healthcare AI applications for clinical summarization, insights generation, and patient analytics.

•Built RAG pipelines over healthcare datasets enabling intelligent retrieval and contextual decision support.

•Designed AI agent workflows for automated analysis and reporting of telehealth data.

•Built healthcare knowledge retrieval and clinical intelligence platforms using RAG architectures, vector databases, and semantic search frameworks.

•Implemented model evaluation frameworks for accuracy, latency, and reliability in clinical AI systems.

•Designed and implemented model monitoring and evaluation pipelines for NLP and ML models.

•Automated CI/CD workflows for ML models including versioning, deployment, and rollback strategies.

•Ensured HIPAA-compliant AI system design with monitoring, logging, and governance frameworks.

•Developed CI/CD automation workflows for ML and AI services using Git-based version control and containerized deployments.

•Implemented AI governance, model monitoring, prompt evaluation, guardrails, and compliance frameworks for regulated healthcare environments.

•Automated healthcare NLP and inference pipelines using TensorFlow, PyTorch, PySpark, REST APIs, and distributed cloud environments.

•Developed intelligent document understanding and medical summarization solutions leveraging AWS Bedrock and foundation models.

•Automated distributed data processing and resource optimization across Databricks and cloud-native compute environments.

•Built NLP pipelines for clinical text processing including summarization and entity extraction.

•Automated predictive analytics workflows and real-time reporting dashboards for healthcare operations.

Technologies: Python, OpenAI, Hugging Face, BERT, SparkNLP, NLTK, spaCy, TF-IDF, Word2Vec, LDA, XGBoost, LightGBM, Scikit-learn, TensorFlow, PyTorch, PySpark, MLflow, Streamlit, GCP, Databricks, Tableau, Power BI, Matplotlib, Seaborn, Oracle, MySQL, MongoDB, Teradata, DB2, Pandas, NumPy, SciPy, SHAP, LIME, asyncio, aiohttp, REST APIs

Dish Network, Englewood, CO August 2017 – May 2019

MLOps / Data Engineer

Responsibilities:

Project: Designed and deployed scalable AI/ML and MLOps solutions for telecom customer analytics, predictive modeling, and intelligent automation supporting millions of subscriber interactions. Built cloud-native data pipelines, NLP systems, and real-time model serving frameworks to improve customer experience, churn prediction, and operational efficiency.

•Built and automated MLOps pipelines for telecom customer analytics, churn prediction, and predictive AI systems.

•Automated ML model deployment, rollback, monitoring, and scaling using Jenkins, Docker, Kubernetes, and Linux automation.

•Developed NLP-based customer analytics solutions including sentiment analysis and text classification.

•Automated distributed model training and batch inference pipelines using PySpark, Hadoop, Hive, and Apache Spark.

•Built AI monitoring automation frameworks for model drift detection, system health tracking, and data quality validation.

•Automated NLP and customer behavior analytics workflows using Scikit-learn, TensorFlow, XGBoost, and NLP libraries.

•Implemented cloud-native automation strategies for scalable model serving, async processing, and distributed AI workloads.

•Supported automated infrastructure provisioning, testing, and deployment processes for enterprise AI platforms.

•Automated telecom operational analytics and intelligent reporting pipelines for customer engagement optimization.

Technologies: Python, FastAPI, Flask, REST APIs, GraphQL, Jenkins, Kubernetes, PySpark, Apache Spark, Hadoop, HDFS, Hive, HBase, TensorFlow, Keras, Scikit-learn, XGBoost, spaCy, Word2Vec, TF-IDF, ARIMA, LSTM, Pandas, NumPy, SciPy, R, Tableau, Oracle, MySQL, Teradata, Linux

Newmont Corporation, Denver, CO February 2014 – July 2017

Data Engineer

Responsibilities:

•Developed automated ETL and DataOps workflows for environmental analytics and compliance reporting using Python, SQL, Hadoop, and PySpark.

•Automated deployment, monitoring, and validation workflows for ML models and analytics services across AWS, Azure, and GCP.

•Built automated anomaly detection, alerting, and predictive analytics pipelines for environmental sensor and operational datasets.

•Automated data ingestion, transformation, reconciliation, and quality validation processes using Python and distributed processing frameworks.

•Developed AI-driven monitoring and alert automation systems using SMTP services and cloud-native observability tools.

•Built automated batch processing and workflow orchestration pipelines using Flume, Hadoop, HDFS, and PySpark.

•Automated backend API processing and concurrent service execution using Python async/await frameworks.

•Implemented automated testing, logging, and model evaluation workflows using pytest and statistical validation techniques.

•Supported infrastructure automation, API deployment automation, and cloud-native DevOps workflows for enterprise analytics systems.

•Improved operational reliability through automated logging, monitoring, data validation, and workflow orchestration processes..

•Used async/await in Python to handle concurrent API calls, reducing response time in backend services.

•Built ETL pipelines in Python to load transactional data into data lakes.

•Automated data reconciliation and anomaly alerting via Python and SMTP.

•Developed Django middleware and forms for secure input handling in dashboards.

•Built batch processors and ingestion scripts using Flume and PySpark for sensor datasets.

•Conducted data cleaning, transformation, and alert rule development using Python, SQL, and pytest.

Technologies: Python, Pandas, NumPy, SciPy, Scikit-learn, Matplotlib, NLTK, Django, React, Bootstrap, FastAPI, Pydantic, REST APIs, R, Tableau, SQL, Oracle, MySQL, PostgreSQL, Teradata, Hadoop, HDFS, TF-IDF, LDA, ARIMA, K-Means, Decision Trees, Random Forest, Logistic Regression, AWS (EC2, ECS, Lambda, CloudWatch), Azure App Services, GCP, PySpark, Flume, pytest, SMTP

EDUCATION

Bachelor of Technology — Computer Science JNTU-H, Hyderabad 2010

Contact this candidate