Skip to content

Hemananda Sai Simhachalam Naidu Singampalli

AI Engineer • Austin, TX • s*******************@gmail.com • +15******056 • drivetube.ai/•••••

Professional Summary

AI Engineer with 4+ years of experience building production-grade generative AI systems and document/voice pipelines for regulated healthcare and credit domains. Strong end-to-end experience fine-tuning LLMs with LoRA/PEFT, running retrieval-augmented generation (RAG) and LangChain agent flows, and serving models on self-hosted vLLM/GPU infrastructure. Hands-on with real-time voice stacks (ASR, TTS, WebRTC), vision-based OCR pipelines, and building evaluation/guardrail frameworks using promptfoo and LLM-as-judge. Experienced in MLOps for model deployment and rollouts using GitLab CI, Ansible blue/green deployments, Docker and Kubernetes, and instrumentation via OpenTelemetry. Proven ability to deliver product outcomes (recovered missed calls, automated billing inputs) while enforcing HIPAA and FHIR constraints and maintaining measurable model evaluation and regression gating.

Technical Skills

Programming Language: Python,Java,SQL
Frontend Technologies: WebRTC
Databases: PostgreSQL,MongoDB,Redis
Cloud Platforms: Azure Blob Storage,Blue,Green Deployment
DevOps & Infrastructure: Docker,Kubernetes
Messaging & Monitoring: OpenTelemetry
Data Analysis & Visualization: Pandas,Power BI
Machine Learning & AI: OCR,GLM-4V,Qwen3-VL
AI/ML Frameworks & Libraries: scikit-learn,XGBoost,LightGBM,ASR
Generative AI & LLMs: LangChain,LoRA,LangGraph,vLLM,Promptfoo,LLM
Vector Databases & RAG: HIPAA
MLOps: MLflow

Work Experience

eMedicalPractice
Delray Beach, FL
AI Engineer
Apr 2026 – Present
Built AI-driven voice and document automation for a healthcare/EHR platform, focusing on HIPAA-safe phone front-door interactions and automated clinical document ingestion.
Tech Stack: Voxtral ASR, Qwen ~3B, vLLM, Pipecat, LangChain, LangGraph, LoRA, promptfoo
  • Architected and deployed a real-time voice AI pipeline using Voxtral ASR and a fine-tuned Qwen ~3B model served via vLLM, achieving a 1s end-to-end first-spoken-response on live calls.
  • Implemented an agentic plan→act→observe loop enabling LLM tool invocations over MCP with intent classification, human-escalation gates and queued task execution using Pipecat and LangChain patterns.
  • Designed a stateful LangGraph-style conversation graph with checkpointed session state and conditional routing to enforce streaming constraints and conversational guardrails.
  • Optimized inference by fine-tuning models with LoRA and self-hosting on GPU nodes, reducing per-call serving cost to approximately $0.30 through model selection and prefix-token caching.
  • Shipped bidirectional, consent-gated voice agents integrated with the EHR phone front door that recovered ~35% of previously voicemail-lost calls, improving access to care workflows.
  • Established an eval-driven safety and correctness pipeline using promptfoo and an LLM-as-judge harness to replay adversarial call scenarios on every merge request and auto-file regressions.
  • Fine-tuned a Qwen3-VL Instruct vision model via LoRA to extract structured CPT-like billing items from scanned clinical notes and emit validated JSON for billing ingestion.
Florida Atlantic University
Boca Raton, FL
Graduate Teaching Assistant
Jan 2025 – Dec 2025
Supported graduate-level data science instruction, focusing on foundational ML concepts and hands-on Python model development for academic coursework.
Tech Stack: Python, Pandas, Scikit-learn
  • Instructed graduate students on supervised learning algorithms and model selection, using Python and Scikit-learn to demonstrate end-to-end model workflows.
  • Designed and led lab sessions covering data preprocessing, feature engineering, and evaluation metrics using Pandas and NumPy.
  • Mentored student projects on hyperparameter tuning and cross-validation, introducing practical validation strategies and experiment tracking.
  • Developed assignment materials and grading rubrics that emphasized reproducibility and code clarity for ML pipelines.
  • Led office hours and project reviews to guide model debugging and visualization using Matplotlib.
  • Evaluated student model performance with precision/recall and AUC metrics and provided detailed feedback to improve experimental design.
Lentra AI PVT Ltd
Pune, India
AI/ML Engineer
Mar 2023 – Dec 2023
Built credit decisioning models and feature pipelines for lending products, focusing on transactional and behavioral data to improve score quality and production reliability.
Tech Stack: XGBoost, LightGBM, Docker, Azure Kubernetes Service, MLflow
  • Directed model experimentation for BREx and GoNoGo credit systems and improved decision accuracy by 15% through feature strategy and model selection.
  • Engineered reproducible feature pipelines from raw transactional data to reduce data preparation bottlenecks and enable faster model iterations.
  • Optimized ensemble models (Random Forest, XGBoost, LightGBM) using cross-validation and Bayesian hyperparameter search, improving AUC from 0.75 to 0.85.
  • Integrated model deployments with Docker and Azure Kubernetes Service to run low-latency scoring and automated retraining triggers using Azure ML.
  • Implemented ML monitoring with MLflow and drift detection to alert and schedule retraining when data distributions changed.
  • Partnered with engineers to containerize scoring services and ensure sub-100ms real-time credit scoring latency for production calls.
Cognizant Technology Solutions
Hyderabad, India
Jr. Software Engineer
Mar 2021 – Feb 2023
Contributed Java backend and Angular frontend components for enterprise web applications across QA, SIT, UAT and Production environments.
Tech Stack: Java, Angular, Swagger, Postman
  • Developed Java backend components and RESTful APIs to support application workflows, validated using Swagger and Postman for contract correctness.
  • Built and integrated Angular web components to deliver reusable UI modules and reduce frontend code duplication across features.
  • Diagnosed and fixed method-level defects and performance issues within Eclipse, improving backend request handling and reliability.
  • Implemented API integrations and data contracts between frontend and backend systems to ensure consistent data flows.
  • Delivered deployment processes across Dev, QA, and Production environments to improve release stability and rollback safety.
  • Authored technical documentation and reusable templates to accelerate onboarding and standardize development practices.

Projects

Medical Document OCR Pipeline
Tools Used: Qwen3-VL, GLM-4V, LoRA, Python, OCR
  • Engineered a vision-model-based OCR pipeline that extracts structured JSON from handwritten and printed clinical documents for automated billing ingestion.
  • Kept the extraction harness model-agnostic behind a unified inference abstraction to swap GLM-4V and a LoRA fine-tuned Qwen3-VL without pipeline changes.
  • Implemented structured-output validation and retry logic to ensure produced JSON met downstream EHR billing schema requirements.
Agentic AI using CrewAI
Tools Used: LangChain, LangGraph, FastAPI, OpenAI
  • Built a multi-agent research orchestration app using CrewAI to coordinate specialized agents for medical research and evidence synthesis.
  • Integrated OpenAI LLMs with a retrieval tool and designed conditional routing and shared state to improve contextual accuracy across agent workflows.
  • Exposed agent orchestration via FastAPI to allow programmatic task submission and result retrieval for downstream analysis.
Text to SQL
Tools Used: GPT-3.5, Python, FastAPI, Streamlit
  • Developed a schema-aware Text-to-SQL service using GPT-3.5 and prompt engineering to translate natural language to accurate SQL queries.
  • Deployed a self-service interface with FastAPI and Streamlit enabling non-technical users to query structured data via natural language.

Education

Florida Atlantic University
Master of Science in Data Science and Analytics (GPA: 3.8) • Boca Raton, FL • Jan 2024 – Dec 2025

Certifications

Microsoft Certified: Azure Fundamentals — Microsoft
Power BI Data Analyst Associate — Microsoft
Neural Networks and Deep Learning — DeepLearning.AI
Python for Machine Learning and Data Science — Udemy
Full Stack Web Development
SQL: Data Reporting and Analysis

Powered by Drivetube · Create your own profile at drivetube.ai

Explore Drivetube

  • Drivetube Profile — your free digital resume — at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept. Documentation.
  • Free Job Board — verified openings crawled ATS-by-ATS from 100,000+ real company career pages across 35 ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed. Documentation.
  • Job Hunt Program — managed job hunting, a one-time purchase from $199.99. JobScout matches verified roles to your real experience band, Blend AI writes a uniquely tailored resume and cover letter for every application, and the Autofill extension fills the form — or Let Us Apply submits it for you. Documentation.
  • Resume Writing Services — human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile. Documentation.
  • Community Membership — from $4.99/month (₹1,999/year in India). Unlocks the gated job-board filters — visa sponsorship, security clearance, workplace and application time — plus Job-Scout AI matching, Resume Report AI, Interview AI prep sheets, Recruiter Outreach AI sent from your own Gmail, Apply or Skip triage, a daily market feed and a $10,000+ library including 23 ATS-validated resume templates. Documentation.
  • Drivetube Hire — for employers — hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do. Documentation.

Full product documentation — every product explained, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.

The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.