Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

AI Engineer with 2.5+ years of hands-on experience building production-oriented Generative AI, RAG, and NLP systems. Skilled in designing end-to-end RAG pipelines (ingestion, chunking, embeddings, vector indexing, semantic retrieval, and grounded LLM responses) and in measuring quality via custom evaluation and before/after benchmarking. Experienced in deploying AI services using FastAPI/REST APIs, Docker, and cloud infrastructure (AWS, Azure, GCP). Delivered measurable impact including improved retrieval relevance, faster release cycles, and increased prediction accuracy through optimization of chunking/retrieval logic and systematic evaluation.…AI Engineer with 2.5+ years of hands-on experience building production-oriented Generative AI, RAG, and NLP systems. Skilled in designing end-to-end RAG pipelines (ingestion, chunking, embeddings, vector indexing, semantic retrieval, and grounded LLM responses) and in measuring quality via custom evaluation and before/after benchmarking. Experienced in deploying AI services using FastAPI/REST APIs, Docker, and cloud infrastructure (AWS, Azure, GCP). Delivered measurable impact including improved retrieval relevance, faster release cycles, and increased prediction accuracy through optimization of chunking/retrieval logic and systematic evaluation.

VENKATA KAUSHIK MITTA





AI Engineer with 2.5+ years of hands-on experience building production-oriented Generative AI, RAG, and NLP systems. Skilled in designing end-to-end RAG pipelines (ingestion, chunking, embeddings, vector indexing, semantic retrieval, and grounded LLM responses) and in measuring quality via custom evaluation and before/after benchmarking. Experienced in deploying AI services using FastAPI/REST APIs, Docker, and cloud infrastructure (AWS, Azure, GCP). Delivered measurable impact including improved retrieval relevance, faster release cycles, and increased prediction accuracy through optimization of chunking/retrieval logic and systematic evaluation.…AI Engineer with 2.5+ years of hands-on experience building production-oriented Generative AI, RAG, and NLP systems. Skilled in designing end-to-end RAG pipelines (ingestion, chunking, embeddings, vector indexing, semantic retrieval, and grounded LLM responses) and in measuring quality via custom evaluation and before/after benchmarking. Experienced in deploying AI services using FastAPI/REST APIs, Docker, and cloud infrastructure (AWS, Azure, GCP). Delivered measurable impact including improved retrieval relevance, faster release cycles, and increased prediction accuracy through optimization of chunking/retrieval logic and systematic evaluation.

Available to hire

AI Engineer with 2.5+ years of hands-on experience building production-oriented Generative AI, RAG, and NLP systems. Skilled in designing end-to-end RAG pipelines (ingestion, chunking, embeddings, vector indexing, semantic retrieval, and grounded LLM responses) and in measuring quality via custom evaluation and before/after benchmarking.

Experienced in deploying AI services using FastAPI/REST APIs, Docker, and cloud infrastructure (AWS, Azure, GCP). Delivered measurable impact including improved retrieval relevance, faster release cycles, and increased prediction accuracy through optimization of chunking/retrieval logic and systematic evaluation.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Language

Javanese

Intermediate

Work Experience

AI Engineer at Ness Digital Engineering

November 1, 2025 - Present

Built LLM-powered enterprise knowledge assistants using Python, LangChain, and OpenAI APIs with Retrieval-Augmented Generation (RAG). Designed end-to-end document intelligence pipelines including ingestion, preprocessing, chunking strategies, embedding generation, vector indexing (FAISS/Chroma), semantic retrieval, and response grounding across enterprise sources. Developed supporting ML workflows using Python, Pandas, NumPy, and Scikit-learn. Productionized AI inference services via FastAPI/REST APIs and Docker on cloud infrastructure for enterprise integration. Implemented CI/CD pipelines with Docker, reducing model release time by 40% and improving consistency between dev and production. Partnered with product/engineering teams to integrate AI automation and reduce manual knowledge lookup effort.

Software Engineer – AI at Secure AIs

August 1, 2025 - November 30, 2025

Developed transformer-based NLP pipelines for sentiment analysis and text classification using PyTorch and Hugging Face workflows. Improved prediction accuracy by 15% using systematic evaluation and hyperparameter tuning. Built scalable preprocessing and feature-engineering pipelines with Python, Pandas, and NumPy for large-scale text datasets. Designed AI microservices for real-time inference using Python, FastAPI/REST APIs, and Docker to enable low-latency integration. Improved model performance via systematic hyperparameter tuning and before/after benchmarking. Collaborated with product teams to deliver AI-driven analytics aligned to business use cases.

Student Assistant / Developer at University of Washington Bothell

June 1, 2024 - June 30, 2025

Managed and validated 800+ student records weekly using Slate CRM and SQL. Built internal reports, forms, and data portals using HTML, CSS, JavaScript, and SQL to improve accessibility and usability. Automated reporting and data extraction workflows using SQL scripting, reducing manual effort and improving reporting turnaround time.

Software Engineer Intern at LTI Mindtree

September 1, 2022 - May 31, 2023

Built healthcare data validation and preprocessing pipelines in Python, Pandas, and NumPy for datasets containing 10K+ patient records, improving data quality for analytics and downstream modeling. Automated data cleaning and transformation workflows, reducing manual processing effort by 40%. Conducted exploratory data analysis and feature extraction to improve dataset usability for machine learning and predictive modeling for healthcare analytics.