Software Engineer · ML Researcher
Dhairya
Mishra
Building AI/ML production systems and full-stack platforms. 4+ years shipping computer vision, NLP, and cloud-native services at scale.
Affiliated With
Featured Projects
Research and production work spanning ML, full-stack, and cloud systems.
Multiplayer Frames
Solaris — Multiplayer Video World Model in Minecraft
First multiplayer video world model generating consistent first-person observations for two players simultaneously, trained on 12.6M frames of coordinated Minecraft gameplay. Published on arXiv, NYU.
Shipped
Teserax.io — Graph-Based AI Thinking Tool
A dual-lane, chat-first exploration tool that transforms linear LLM chat into a visual, non-linear graph canvas with AI orchestration, crosslink reasoning, multi-model BYOK support, and cloud persistence — shipped v2.0 with 64 issues closed across 5 development phases.
Accuracy
Cloud NLP Classification Service
Production-ready multi-model text classification service with zero-downtime model switching, deployed on GCP. DistilBERT achieves 96.57% accuracy.
Accuracy
MRI Brain Tumor Detection & Segmentation
Multimodal MRI classification and segmentation model trained on BraTS dataset with shared encoder, achieving 91.3% accuracy and 97.1% sensitivity.
Skills & Technologies
Full-stack proficiency across ML/AI, cloud infrastructure, and modern web frameworks.
Languages
ML / AI
Cloud & DevOps
Frameworks
Data & Storage
Testing & Observability
Experience Timeline
AI Analyst Intern
Jan 2026 — PresentEvidenza · Brooklyn, NY
Engineered a multimodal creative feature-extraction pipeline using SAM-style segmentation, object detection, and video/image processing to compute 12+ per-ad signals (dominant color, objects, people count, duration), achieving 95% feature coverage
Built Spark-based ETL for recurring backfills and heavy joins across YouTube metadata and extracted creative signals; centralized 5000+ B2B ads in MySQL (Hive) and trained performance models (CTR, engagement, completion rate), driving a 34% engagement lift via recommendation outputs
Scaled synthetic persona workflows (25 new personas/week, 2 runs/week) and defined human-vs-synthetic evaluation gates using a 50-user audit set; enforced ≥65% agreement as a production acceptance threshold
Sr. Software Development Engineer
Jan 2023 — Jan 2025CVS Health · New York, NY
Piloted an AI-driven image-to-text CI automation using Hugging Face Transformers. Established production-grade pipelines for enterprise rollout and reduced downstream defects by 15%
Delivered an internal RAG support assistant leveraging Slack integrations with OpenAI and ChromaDB. Accelerated self-serve troubleshooting for teams and reduced manual ticket resolution time by 20%
Reviewed and shipped 125+ PRs and owned on-call for customer-facing core platform systems (Digital-Blocks 2.0, Experience Builder) serving millions of customers daily; reduced downtime by 12%
Built OpenTelemetry-to-Grafana observability + synthetic tests for scale events across deployed applications and microservices; improved debugging efficiency 25% (median incident MTTR)
Implemented automated UI quality gates by integrating axe-core with Playwright into GitHub Actions pipelines; shifted validation left across supported repos and cut production issues by 35%
Advanced Software Developer
Feb 2022 — Jan 2023Aetna Health · New York, NY
Developed testing automation suite CAT, RallyScore, and ThemeScore; reduced QA time by 75%
Designed Rally kanban migration pipeline for 600+ nested structures; reduced migration time by 80%
Provisioned encrypted API microservices for MongoDB access; boosted data transaction speeds by 55%
Education
New York University
Courant Institute
M.S. Computer Science (AI)
Trine University
B.S. Software Engineering & Mathematics
Let's Build Something
Interested in collaborating on ML research, full-stack systems, or production AI? I'd love to hear from you.