AI/ML Engineer with production experience across cloud-native infrastructure (Kubernetes, Terraform, CI/CD), now designing multi-agent systems with human-in-the-loop approval and evaluation harnesses.
Pick an incident, then approve or reject the fix. Nothing touches a cluster until a human says so, which is the point of the design.
Answer a few Python questions. Bayesian Knowledge Tracing updates mastery after each first attempt, SM-2 schedules the next review, and wrong answers get Socratic hints that never give the answer. A simplified demo of the approach, not the production agent.
An LLM assistant grounded only in my resume and project facts. If it doesn't know, it says so.
Multi-agent system that triages Kubernetes incidents from Prometheus/ELK signals, diagnoses root cause with cited evidence, and gates every remediation behind human approval. Scored by an eval harness for diagnosis and remediation accuracy, with its own tool-call latency and success rate in Prometheus. Try the demo →
Adaptive tutor combining Bayesian Knowledge Tracing and SM-2 spaced repetition, with a Socratic hint agent constrained in code never to reveal answers. A synthetic-student eval showed a 19-point true-mastery lift over a static curriculum on the same practice budget.
RAG system for document Q&A: ingestion, chunking, embedding and semantic search over a vector database, returning citation-backed answers. Served via FastAPI and containerized with Docker.
Handles customer banking queries (loans, policies, fraud checks) with LangGraph orchestrating tool-calling agents that query PostgreSQL and external APIs.
End-to-end churn pipeline: feature engineering, training and MLflow experiment tracking, served through a FastAPI endpoint for real-time prediction and containerized with Docker.
Filter by area. Green-outlined chips are recent additions.
Manognya learns fast and takes on new challenges without being asked. She finishes tasks efficiently, keeps sharpening her DevOps and AWS skills, and readily helps teammates learn and get their work done. Her professionalism and positive attitude make her a valuable member of the team, and I'm confident she will keep growing.
Open to AI Engineer, ML Engineer and Cloud DevOps roles. Based in Hyderabad, India, and happy to work remote or relocate.