About nidhi
AI/LLM Engineer with 8+ years of experience building scalable machine learning and LLM-powered applications across financial services, insurance, and retail domains.I specialize in designing intelligent systems using Large Language Models, Retrieval-Augmented Generation (RAG), and Agentic AI architectures. My work focuses on building context-aware, production-grade AI systems that can reason, retrieve knowledge, and execute multi-step tasks autonomously.Currently, I design and deploy end-to-end LLM and agent-based systems for credit risk analysis, fraud detection, and customer intelligence using tools like LangChain, FAISS, Pinecone, and cloud platforms such as GCP Vertex AI and AWS SageMaker.Core expertise: * LLM Applications: RAG pipelines, prompt engineering, semantic search * Agentic AI: Tool-based reasoning, multi-step workflows, API integrations * ML & NLP: Transformer models, PyTorch, Hugging Face * MLOps: Deployment, monitoring, CI/CD, retraining pipelines * Data Engineering: PySpark, Airflow, KafkaI enjoy solving complex problems at the intersection of AI, data, and real-world business impact—especially where intelligent systems can automate decision-making and unlock insights at scale.Open to opportunities in Generative AI, LLM systems, and advanced ML engineering.
Key Skills
Experience
Ai / Llm Engineer
CurrentKearny Bank
* Built and deployed end-to-end LLM-powered and Agentic AI systems for credit risk analysis and fraud detection using large-scale financial datasets * Designed RAG pipelines integrating LLMs with FAISS and Pinecone for contextual and explainable insights * Developed agent-based workflows using LangChain enabling multi-step reasoning, tool usage, and API interactions * Implemented LLM agents for SQL querying, document retrieval, and automated risk investigation * Built semantic search and embedding pipelines for structured and unstructured financial data * Deployed scalable AI systems on GCP Vertex AI supporting real-time and batch inference * Developed high-performance APIs using FastAPI for low-latency AI inference * Improved latency using Redis caching and optimized retrieval strategies * Built evaluation frameworks for prompt quality, hallucination detection, and response scoring * Implemented CI/CD pipelines and monitoring for production AI systems
Ai / Ml Engineer
Hm Insurance Group
* Built fraud detection models using XGBoost improving accuracy by 22% and reducing losses by $1.5M annually * Deployed ML models on AWS SageMaker with real-time APIs achieving sub-200ms latency * Designed real-time data pipelines using Apache Kafka for streaming data processing * Automated workflows using Apache Airflow for model retraining and feature updates * Tracked experiments and model performance using Weights & Biases (W&B) * Developed scalable ML APIs and microservices for enterprise integration
Data Scientist
Ascena
* Built data pipelines and performed large-scale analysis using Python (Pandas, NumPy) and SQL * Developed Power BI dashboards to track sales, inventory, and business KPIs * Conducted statistical analysis to identify key drivers of customer behavior and sales performance * Integrated multiple data sources to improve analytics and reporting accuracy * Collaborated with business teams to deliver actionable insights
Education
Gujarat University
Bachelors
Interested in connecting with nidhi?
Sign up for NinjaHire to send a connection request.
Common Questions
What is nidhi's expertise?
nidhi specializes in LLM Engineer - Remote, with expertise in apache airflow, apache kafka, docker, faiss, fastapi.
Where is nidhi located?
nidhi is based in jersey city, new jersey, united states.
How much experience does nidhi have?
nidhi has 9+ years of professional experience.
How can I contact nidhi?
You can connect with nidhi through NinjaHire by signing up for a free account.
Other LLM Engineer - Remotes
Looking for a different LLM Engineer - Remote?
Describe exactly who you need and NinjaHire will source them for you.
Type a role to try NinjaHire for free