Anish Ghule
Founding Software AI Engineer
Founding Software AI Engineer at RISA in Palo Alto, California. Building intelligent systems with Applied GenAI, LLM orchestration (OpenAI, Anthropic, Gemini, TogetherAI), Model Context Protocol (MCP), Agent-to-Agent (A2A) protocols, and cloud-native backend architecture. CS graduate from BITS Pilani (9.4/10 GPA, 80% merit scholarship) with research experience at the Indian Institute of Science (IISc).
Experience
Founding Software AI Engineer - RISA (Jul 2024 — Present, Palo Alto, CA)
Founding AI Engineer architecting intelligent healthcare automation systems. Built AI Agent Factory for vendor-agnostic LLM orchestration across OpenAI, Anthropic, Gemini, and TogetherAI using Abstract Factory and Adapter patterns. Pioneered Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocols for dynamic tool discovery. Reduced order ingestion from 75 to 7 minutes (10x improvement). Built PDF Parser Agent and NAR Grid automation achieving >15% zero-touch clinical prior authorization processing. Designed FHIR R4 Transformers with Hexagonal/Adapter patterns.
Software Engineering Intern - Sprinklr (Jan 2024 — Jun 2024, Gurugram, India)
Infrastructure resiliency and observability for enterprise-scale Kubernetes deployments. Implemented resiliency checks for CPU underutilization/overusage; identified issues in 60%+ deployments. Developed proactive jobs for Elasticsearch shard mapping.
Research Intern - Indian Institute of Science (IISc) (Mar 2022 — Dec 2023, Bangalore, India)
Micro-expression emotion recognition research under Dr. Punit Rathore. Designed architecture using Vision Transformers and Masked Auto Encoders. Achieved +11% accuracy improvement on SAMM and CASME2 benchmarks, outperforming state-of-the-art.
SDE Intern - Sprinklr (May 2023 — Jul 2023, Gurugram, India)
Backend development and cloud cost optimization. Deployed restricted APIs via SpringBoot; reduced Elasticsearch storage costs ~30%. Developed Azure Cost Analyzer with 12 drill-down views.
R&D Intern - Soroco (Aug 2022 — Apr 2023, Bangalore, India)
Process mining and intelligent automation using NLP and LLMs. Devised rule-engine to summarize action events. Generated natural language descriptions using heuristics and GPT-3.
Research Intern - CSIR-CEERI (May 2022 — Jul 2022, Chennai, India)
Remote photoplethysmography (rPPG) research under Dr. Madan Lakshmanan. Implemented Eulerian Video Magnification for remote heart rate estimation.
Projects
AI Agent Factory
Vendor-agnostic LLM orchestration framework using Abstract Factory and Adapter patterns. Supports OpenAI, Anthropic, Gemini, TogetherAI with dynamic tool discovery via MCP and A2A protocols.
Multi-Retriever Closed Domain QA — Read Paper (PDF)
Closed-domain QA pipeline using HayStack with dual retriever (DPR), FARMReader, and Re-Ranker. Achieved +9.6% F1-Score improvement on CovidQA dataset.
Text2Image Generation — Read Paper (PDF)
GAN-based architecture for generating high-fidelity Indian facial images from textual descriptions. Curated 1500+ annotated images; fine-tuned StyleGAN, TediGAN, CLIP.
Image2Image Manipulation based on Text Prompt — Read Paper (PDF)
Text-guided image manipulation using GAN-based architectures. Leverages CLIP embeddings for semantic alignment between text prompts and image transformations.
Conversational AI & UX Study
Field study on AI conversational agents' UX. Multi-class classification of entities in customer complaints using Regression, SVM, and XGBoost on CFPB dataset.
Azure Cost Analyzer
Dashboard tool with 12 drill-down views for Azure cloud cost analysis and forecasted time-series visualization using Kibana.
Research
Micro-Expression Emotion Recognition via Vision Transformers (IISc Bangalore, 2022 — 2023)
Designed ViT + Masked Auto Encoder architecture trained on custom multi-angle facial dataset. Achieved +11% accuracy improvement on SAMM and CASME2 benchmarks, outperforming CNN baselines (ResNet, VGG-16).
Remote Photoplethysmography via Eulerian Video Magnification (CSIR-CEERI, 2022) — GitHub
Implemented spatio-temporal decomposition with bandpass filtering for color amplification in YIQ space. Generated 20x magnified videos for remote heart rate estimation.
Multi-Retriever QA Pipeline for COVID-19 Literature (BITS Pilani, 2022 — 2023)
Authored closed-domain QA pipeline with dual retrievers and re-ranking. Fine-tuned BERT on CORD dataset achieving 81.6% F1-Score on CovidQA.
Skills
Python, PyTorch, TensorFlow, LangChain, OpenAI, Anthropic, FastAPI, Java, SpringBoot, JavaScript, React, Kubernetes, Docker, GCP, AWS, Azure, PostgreSQL, Elasticsearch, MongoDB, Git, Linux, CLIP, GANs, Vision Transformers, BERT
Education
B.E. Computer Science - BITS Pilani (2020 — 2024)
9.4/10 GPA | 80% Merit Scholarship (top 3%) | IEEE ML SIG Head | TA for 6 courses across 5 semesters
Contact
ghuleanish12@gmail.com |
LinkedIn |
GitHub |
X / Twitter
This portfolio requires JavaScript for the full interactive experience. Please enable JavaScript and refresh the page.