Naveen P.
Generative AI Engineer
Experience
Jan 2025 - Nov 2025
11 monthsHyderabad, India
Generative AI Engineer
Emscale
- Implemented prompt engineering strategies to enhance model reliability and consistency, achieving a 15% improvement in output quality across diverse client use cases.
- Collaborated with cross-functional teams to design, test, and deploy agentic AI solutions that streamlined data processing pipelines, increasing system efficiency and scalability.
- Developed and refined AI-driven workflows leveraging large language models to improve task automation accuracy by 25%, reducing manual intervention and turnaround time.
- Developed and fine-tuned generative AI models leveraging large language architectures to automate content synthesis, improving response coherence and contextual accuracy by 20%.
- Designed and implemented RAG-based intelligent agents for healthcare insurance, financial analytics, and customer service domains using LangChain, LangGraph, and AWS Bedrock LLMs, enabling context-aware document retrieval and automated insights generation.
- Architected end-to-end RAG pipelines leveraging Amazon S3 for vectorized document storage and AWS MemoryDB for low-latency caching, optimizing retrieval speed by 40% and ensuring real-time query responsiveness.
- Integrated Bedrock-hosted LLMs (Claude, Titan) with custom retrieval layers using FAISS and LangChain retrievers, improving factual accuracy and reducing hallucination rates by 30%.
- Implemented Model Context Protocol (MCP) to enable interoperable agent communication between LLMs, retrieval tools, and memory systems, enhancing modularity and multi-agent coordination.
- Developed domain-specific RAG agents for healthcare insurance workflows, such as claim summarization, policy Q&A, and compliance validation, improving operational efficiency and policy accuracy by 35%.
- Applied responsible AI practices, including bias detection, explainability (SHAP, LIME), and compliance with GDPR and EU AI Act, ensuring ethical and auditable agentic decision-making.
- Collaborated with data engineers, ML scientists, and domain experts to productionize scalable agentic AI systems on AWS infrastructure using CI/CD pipelines and secure IAM roles.
- Implemented observability tools like Langfuse and LangSmith for agent traceability, response evaluation, and quality monitoring, achieving consistent reliability across diverse client use cases.
- Optimized LLM prompt engineering strategies for multi-turn conversational agents, improving response quality consistency by 15% and reducing manual fine-tuning cycles.
- Documented and benchmarked RAG agent performance metrics, including latency, context retention, and retrieval accuracy, contributing to continuous system improvement and SLA compliance.
Jan 2022 - Jan 2025
3 years 1 monthLondon, United Kingdom
AI/ML Engineer
DHL Supply Chain
- Developed reinforcement learning-based dynamic routing algorithms for last-mile delivery optimization, incorporating agentic AI principles to enable autonomous decision-making, reducing transportation costs by 10% and enhancing operational efficiency.
- Designed NLP-based sentiment analysis solutions using BERT and LLMs, integrating responsible AI techniques for bias mitigation and explainability, improving client satisfaction by 18% while ensuring ethical data handling.
- Built a warehouse optimization tool with clustering algorithms and multi-agent reinforcement learning (MARL) approaches, improving storage efficiency by 15% through collaborative agentic systems.
- Implemented demand forecasting models with ARIMA, Prophet, and transformer-based techniques, applying RAG for enhanced accuracy and incorporating fairness evaluations to align with responsible AI standards.
- Mentored junior data scientists on reinforcement learning best practices, agentic AI frameworks (e.g., LangChain), and ethical AI deployment, reducing training times by 30% and fostering a culture of responsible innovation.
- Collaborated on predictive analytics projects, emphasizing AI security and privacy-preserving models to comply with GDPR and EU AI Act regulations.
Mar 2021 - Mar 2022
1 year 1 monthLondon, United Kingdom
Data Scientist Internship
Bright Network
- Built predictive models for customer behavior analysis using logistic regression, decision trees, and reinforcement learning methods, leading to a 20% increase in retention while implementing bias detection for fair outcomes.
- Analyzed datasets with clustering and regression techniques, providing insights for data-driven decisions and integrating explainable AI (XAI) tools like SHAP to ensure transparency in agentic AI prototypes.
- Created data visualizations with Power BI and Matplotlib to communicate analytical insights, focusing on ethical AI visualizations that highlight bias and fairness metrics.
Summary
Innovative Generative AI Engineer with 4 years of experience developing autonomous systems, reinforcement learning models, and ethical AI solutions. Skilled in LangChain, LangGraph, Stable-Baselines3, and OpenAI API, with proven expertise in prompt engineering, RAG-based intelligent agents, and multi-agent collaboration. Delivered measurable results including a 40% improvement in operational efficiency, a 25% gain in automation accuracy, and a 30% reduction in hallucination rates through optimized generative AI models. Adept at implementing responsible AI practices aligned with GDPR, CCPA, and EU AI Act compliance, ensuring explainability, fairness, and transparency in large-scale AI applications.
Languages
English
AdvancedGerman
IntermediateJapanese
IntermediateEducation
Mar 2019 - Mar 2022
University of Hertfordshire
Master in Data Analytics & AI in Data Science · Data Science · London, United Kingdom · 2:1
May 2014 - Dec 2018
SRM University
Bachelor in Computer Science & Engineering · Computer Science & Engineering · Chennai, India · 3.5
Certifications & licenses
Agentic Al
DeepLearning.ai
GitGub Copilot Certification
Codecademy
RAG And Agentic Al Professional Certification
IBM
Multi Agent Systems Using CrewAI
DeepLearning.ai
Al Governance
DataCamp
Designing Agentic Systems With LangChain
DataCamp
Gen Al For Cybersecurity Specialization
IBM
Knowledge Graphs Certified Professional
Neo4j
Prompt Engineering Specialization
Reinforcement Learning From Human Feedback (RLHF)
DataCamp
Vector Databases Professional Certification
Weaviate
Need a freelancer? Find your match in seconds.
Try FRATCH GPT More actions
Similar Freelancers
Discover other experts with similar qualifications and experience
- English
- Deutsch
2025 © FRATCH.IO GmbH. All rights reserved.