AI Engineer with less than a year in LLM, DevOps, and Machine Learning
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Highly motivated and skilled AI Engineer currently pursuing a Master's in Computer Applications. Proficient in a wide array of technical skills including Python, TensorFlow, Kubernetes, and Node.js. Extensive experience in developing multi-agent LLM systems, predictive analytics, and end-to-end CI/CD pipelines. A proactive problem-solver with a strong background in competitive programming and open-source contributions, eager to leverage advanced AI/ML capabilities for innovative solutions.
PSG College of Technology
Master of Computer Applications
August 1, 2024 – June 30, 2026
Dr. N.G.P. Arts and Science College
B.Sc Information Technology · Information Technology
August 1, 2019 – April 1, 2022
IMDB Sentiment Analysis RNN with End-to-End Eval Pipeline
June 1, 2026 – Present
Designed a SimpleRNN (10K vocab, 500-token sequences) for binary sentiment classification; built eval pipeline with early stopping callbacks and quantitative metrics to detect output degradation and guide architecture decisions. Wrote unit and integration tests for NLP preprocessing and model inference; deployed as Streamlit app containerized with Docker, published to Hugging Face Spaces demonstrating full AI-native development end-to-end.
View ProjectCI/CD Pipeline Automated Testing, Instrumentation & Quality Gates
June 1, 2026 – Present
Engineered end-to-end CI/CD pipeline with automated test generation, security scans (Trivy, Gitleaks), and SonarQube quality gates; added failure triage logging across every stage providing full log analysis and observability into build, test, and deployment failures. Added instrumentation and monitoring across pipeline stages – build metrics, test result aggregation, deployment health checks – enabling rapid failure diagnosis; achieved zero-downtime rolling deployments on AWS EC2 with high code coverage, cutting deployment time significantly.
View ProjectMulti-Agent LLM Developer Productivity Platform
June 1, 2026 – Present
Architected an end-to-end multi-agent pipeline integrating Gemini LLM API with structured prompt engineering for context-aware code assistance; coordinated LLM tool use across agentic workflows with iterative prompt tuning to actively mitigate LLM failure modes – hallucination, context limits, and tool misuse. Built an LLM evaluation system to measure agent output quality, authored test cases against expected completions, performed failure triage and log analysis on degraded responses, and iterated on prompt strategies to raise quality scores measurably. Instrumented the API layer with structured logging and LeetCode cache telemetry reducing redundant API calls significantly; implemented JWT-based auth with RBAC, optimized MongoDB indexing, and documented system design specs for team onboarding.
View ProjectCustomer Churn Prediction ANN with Evaluation Framework
June 1, 2026 – Present
Built a multi-layer ANN in TensorFlow/Keras for binary classification; designed an evaluation framework with stratified splits, dropout regularization, and quality metrics to analyze failure patterns and diagnose model degradation; authored unit tests validating data integrity and inference outputs at every preprocessing stage (label encoding, scaling, one-hot encoding, Word2Vec). Deployed real-time prediction dashboard via Streamlit and exposed inference as a REST API; documented architecture, data schema, and API contracts for team onboarding.
View ProjectPredictive Source Code Risk Assessment using Machine Learning
CONCAVE
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project portfolio demonstrates a strong alignment with an AI Engineer role, showcasing diverse applications of machine learning and AI, including NLP, predictive modeling, and LLM-based systems. The focus on end-to-end development, MLOps, and quality engineering practices aligns well with modern software development cultures. Open-source contributions and competitive programming suggest a collaborative and growth-oriented mindset. The candidate is currently pursuing a Master's degree, indicating a commitment to continuous learning and academic rigor. The projects are all personal, which is typical for a candidate with no professional experience, but they are substantial and well-described.
Soft Skills & Operational Fit
The candidate's project descriptions highlight an ability to work on complex, end-to-end systems, suggesting strong problem-solving and system thinking skills. The emphasis on evaluation frameworks, failure triage, and instrumentation points to a detail-oriented and quality-focused approach. Open-source contributions and competitive programming indicate a proactive learning attitude and ability to collaborate. The lack of professional experience means operational fit in a corporate setting is yet to be fully proven, but the project work suggests a good foundation.