AI Engineer with 1+ years in Machine Learning & Generative AI
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 results-oriented AI Engineer specializing in Machine Learning, Deep Learning, and Generative AI. Proven ability to design and implement complex AI systems, including multi-modal agentic pipelines and knowledge-based RAG systems. Skilled in Python, PyTorch, TensorFlow, and various LLM frameworks, with hands-on experience in cloud deployment and MLOps practices. A strong academic background in Artificial Intelligence and Data Science, complemented by a track record of impactful research and contributions to cutting-edge AI projects.
Indian Institute of Information Technology Design and Manufacturing Kurnool
B.Tech · Artificial Intelligence and Data Science
August 1, 2022 – June 30, 2026
National Institute of Technology Karnataka, Surathkal
AI Summer Intern
June 1, 2025 – August 31, 2025
India
BrightCandy.ai
AI Product Intern
May 1, 2025 – June 30, 2025
India
Samsung PRISM
AI Research Intern
June 1, 2024 – December 31, 2024
India
PodSearch AI – Multi-Modal Agentic Research Intelligence System
June 16, 2026 – Present
• Orchestrated a multi-agent LangGraph pipeline with web search and vector memory for automated research and podcast generation. • Engineered a self-correcting agent workflow with critic-based validation, retry mechanisms, and fault-tolerant orchestration across AI agents. • Developed a secure multimodal ingestion framework supporting text, image, PDF, and speech inputs. • Created a Streamlit observability dashboard for agent monitoring, memory retrieval, and podcast generation, containerized with Docker.
View ProjectSelf-Correcting MCP Data Analyst Agent
June 16, 2026 – Present
• Designed a agentic orchestrator using MCP and Groq Llama-3.3-70B, enabling dynamic tool discovery and multi-step ReAct reasoning. • Implemented a self-reflection engine that critiques and corrects LLM-generated SQL/Python code before execution, reducing hallucination. • Unified database and analytical tools through a single function-calling API, with autonomy over data querying, EDA and visualisation. • Enabled ingestion of 5+ file formats using automated schema inference and Tesseract OCR.
View ProjectEnterprise Financial Knowledge RAG System
June 16, 2026 – Present
• Built a Dockerized hybrid RAG pipeline using BM25 and BGE sparse-dense fusion, reliably serving over 10K daily queries with low latency. • Reduced query latency by 75% through MiniLM cross-encoder reranking combined with Reciprocal Rank Fusion for more precise results. • Optimized LLM inference costs by 40% using a Redis Stack semantic cache delivering sub-100ms hits at a 35% cache rate. • Integrated RAGAS for automated evaluation, catching 95% of hallucinations and eliminating 80% of manual QA overhead. • Deployed async FastAPI endpoints with Ollama for token-level streaming, consistently achieving under 500ms Time-to-First-Token.
View ProjectMulti-Label Classification in Remote Sensing [WACV 2026]
June 16, 2026 – Present
• Designed a multimodal pipeline combining cVAE and a dual GNN to extract joint spatial embeddings from aerial and Sentinel-2 satellite data. • Demonstrated 85% Micro-F1 and 76% mAP, outperforming state-of-the-art models including ESRGAN, LDMSR, RCAN, and AE baselines. • Applied curriculum learning and uncertainty-weighted loss optimization to fuse heterogeneous modalities and mitigate severe class imbalance across 19 land-cover categories, improving rare-class recall by 22% on a dataset of 100K+ satellite image patches.
View ProjectCultural Fit Analysis
The candidate demonstrates a strong cultural fit for an AI Engineer role through diverse projects spanning agentic AI, RAG, and computer vision, indicating adaptability and a broad interest in AI applications. Their involvement in academic research and personal projects showcases initiative and a passion for the field. The experience with various tools and frameworks suggests a willingness to learn and integrate new technologies, which is crucial in a fast-evolving domain like AI.
Soft Skills & Operational Fit
The candidate's project descriptions and internship experiences suggest strong problem-solving abilities, a proactive approach to engineering complex AI solutions, and an understanding of deployment and operational aspects (CI/CD, monitoring, cost optimization). The self-correcting mechanisms in their projects indicate attention to robustness and reliability. The academic publication also points to strong research and analytical skills.