Path
Scope, over time
Four eras, 20 systems. Each role below links out to everything shipped during that stretch.
Principal ML Engineer
Own technical direction and code standards across an ML/backend team.
8 systems shipped this era
Multimodal Agent Platform
A unifying platform bringing multiple analytical capabilities — scoring, root-cause analysis, screen analysis, and search — under one extensible system.
Multi-Agent Query Routing
Chain-of-thought routing across domain-specific subagents for structured query resolution.
Ambiguous Query Decomposition
AI agents that break down vague search queries and dynamically convert variable fields into structured metadata filters.
Long-Context Video Retrieval
Q&A over multi-hour video via chunked, sentence-level retrieval — exposed through a chat interface and an MCP-based agent.
LLM-as-Judge Evaluation
An LLM-based scoring approach benchmarked against golden datasets, with a human-in-the-loop feedback cycle.
Automated Root Cause Analysis
A framework-driven RCA system surfacing systemic patterns across call, chat, and email transcripts.
Behavioral Screen Analytics
An analyzer extracting structured operational data — actions, idle time, errors — from raw screen recordings.
Event-Driven SLA Pipeline
A real-time event pipeline built to hit a strict latency SLA, with idempotent handling and multi-source validation.
Senior ML Engineer
Lead a team of ML engineers building retrieval and LLMOps platforms, from architecture to deployment.
4 systems shipped this era
Incremental Vector Search
Semantic search over a continuously refreshing index — retrieval that stays current without a full rebuild.
LLMOps Training & Deployment Platform
An end-to-end automated platform covering data versioning, training runs, model artifacts, evaluation, and deployment.
Document Semantic Matching
A similarity-matching engine reconciling extracted document data against system records using configurable business rules.
Zero-Shot NER at Scale
Applying large language models for zero-shot named-entity recognition across a wide range of document types.
ML Engineer I / II
Owned NER, classification, and object-detection pipelines; mentored junior engineers.
5 systems shipped this era
Custom AutoML Tooling
An in-house hyperparameter-optimization tool for text classification, cutting exploration time from weeks to days.
Object Detection Pipelines
End-to-end object detection pipelines covering data processing, model building, evaluation, and deployment.
Distributed Training Infrastructure
Multi-worker distributed training and pipeline infrastructure built on Kubeflow, with Docker-based deployment.
Classical Text Extraction
Structured text extraction combining statistical models, neural networks, and hand-tuned pattern matching.
Containerized ML Deployment
A containerized build and publishing pipeline standardizing how trained models moved from experimentation into scheduled jobs.
Software Engineer, Trainee → Intern
Started with classical ML and rule-based text systems before the deep-learning shift.
3 systems shipped this era
Classical Text Classification at Scale
A comparative approach to document classification spanning traditional ML models and early neural methods across a wide range of document types.
Lightweight Model Serving
Backend prediction services built around in-memory model loading, minimizing latency for real-time inference requests.
Automated Classification & Reporting
Pattern-based text classification paired with automated evaluation reporting on accuracy, precision, recall, and F1.