Ramavath Santhosh
AI EngineerAI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI Engineer with 1+ years in ML Systems & NLP, GenAI
AI/ML Engineering with nearly 2 years of experience designing, delivering, and scaling enterprise AI solutions across healthcare, financial services, and retail domains. Strong expertise in Generative AI, Agentic AI, and Vector Databases, with proven success building production-grade LLM systems beyond POCs in regulated enterprise environments. Demonstrated ownership of end-to-end AI program execution, translating enterprise AI strategy into roadmaps, technical architectures, agile backlogs, and measurable business outcomes. Hands-on leader in AI Governance and Responsible AI, driving AIRB-aligned reviews, ethical risk mitigation, model documentation, explainability, and compliance in healthcare systems. Deep experience across the full ML lifecycle, from data ingestion and feature engineering to deployment, monitoring, drift detection, and long-term operational reliability. Strong background in healthcare NLP, including clinical document intelligence, claims processing, metadata extraction, and intelligent assistants for clinicians and operations teams. Recognized technical mentor with experience leading engineers, conducting design reviews, code reviews, and developing high-performing AI engineering teams.
TKR College of Engineering & Technology
B.Tech · Computer Science & Engineering - Data Science
August 1, 2021 – June 30, 2024
DR. B. R. AMBEDKAR JUNIOR COLLEGE
Intermediate · Mathematics, Physics, Chemistry
June 1, 2019 – May 31, 2020
JAMA-E-OSMANIA –OU
SSC
N/A – May 31, 2018
SAK Informatics
AI/ML Engineer
January 1, 2025 – Present
India
SAK Informatics
AI/ML Engineer
January 1, 2024 – December 31, 2025
India
Secure Digital Evidence Storage System
January 1, 2025 – June 30, 2026
Developed a secure web-based digital evidence management system using Flask for handling sensitive forensic data in cloud environments. Implemented AES-256 encryption to ensure confidentiality of stored digital evidence and protect against unauthorized access. Integrated SHA-256 hashing for data integrity verification, enabling detection of tampering and ensuring evidence authenticity. Designed and enforced Role-Based Access Control (RBAC) with request-based authorization workflows for controlled and secure multi-user access. Built a comprehensive audit logging mechanism to track user actions, improving accountability and traceability across the evidence lifecycle. Utilized Lightning Memory-Mapped Database (LMDB) for high-performance storage with fast read/write operations and transactional consistency. Developed a secure cloud-compatible architecture to handle distributed access and mitigate risks such as insider threats and data breaches. Automated secure evidence upload, storage, retrieval, and verification processes, reducing reliance on manual intervention. Enhanced system reliability by combining encryption, hashing, and access control mechanisms for end-to-end data protection.
UPI Fraud Detection System using ML & DL
January 1, 2024 – December 31, 2025
Developed a web-based fraud detection system for UPI transactions using Flask, enabling secure and real-time prediction of fraudulent activities. Implemented Natural Language Processing (NLP) techniques with Sentence-BERT to generate contextual embeddings from transaction data. Designed and trained multiple classification models including Gaussian NB, Bernoulli NB, Multinomial NB, and Histogram-based Gradient Boosting (HGB). Achieved high accuracy and improved performance metrics (Precision, Recall, F1-Score) with the proposed HGB model, outperforming traditional approaches. Built a multi-aspect detection system supporting both binary classification (fraud vs non-fraud) and multi-class classification (transaction types). Enabled real-time fraud prediction with automated data processing, reducing dependency on manual verification methods. Developed a secure login-based interface allowing users to upload datasets and download prediction results. Improved system scalability and efficiency by handling large-scale and dynamic transaction datasets. Integrated end-to-end ML pipeline including data preprocessing, feature extraction, model training, evaluation, and deployment. Reduced false positives and enhanced detection capability for complex fraud patterns in digital payments.
Cultural Fit Analysis
The candidate's projects demonstrate a focus on practical, problem-solving applications of AI/ML in areas like fraud detection and secure data management. This indicates a results-driven approach. The breadth of technical skills listed, including various ML models, NLP techniques, and security mechanisms, suggests adaptability and a willingness to learn diverse technologies. The experience, though limited in duration, shows a consistent application of AI/ML principles. The target role of AI Engineer aligns well with the candidate's demonstrated project work and technical skills.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to take ownership of end-to-end system development, from design to deployment. The focus on secure systems and real-time prediction suggests a practical, results-oriented approach. The mention of improving system scalability and efficiency points to an operational mindset. However, without direct interview data, assessing collaboration, stress handling, or leadership soft skills is not possible.