Hire Me
Open to freelance AI/ML projects

Saicharan Pittala, AI and Machine Learning Engineer

I build AI that works in production.

LLM agents, RAG systems and machine learning models for teams that need accuracy, speed and cost under control. 4+ years of experience, based in Hyderabad, India, working with clients worldwide.

See my workEmail me

LangGraphLangChainOpenAIAzure OpenAIPineconeFAISSPyTorchFastAPIDockerAWSMLflowPython

40%fewer front-desk queries, 1,000+ patients served
50%faster radiology report drafting
10 to 3 minto review a lab report
15%better risk prediction accuracy

What I build

I take on a limited number of freelance projects alongside my full-time role. Bring a clear problem and I deliver a working, deployed solution.

RAG and document Q&A

Chat over your PDFs, wikis or databases, with evaluation.

AI agents and Text-to-SQL

LangGraph agents that query your data safely in plain English.

LLM fine-tuning

LoRA/PEFT adaptation to your domain at lower cost.

Document AI

OCR and LLM pipelines for scans, reports and forms.

Predictive ML models

Risk scoring, classification and anomaly detection.

Deployment

FastAPI services in Docker on AWS or Azure.

Selected work

What I built, the stack behind it, and what changed for the business.

ChemAnalyst, 2026

SQL Agent: ask in English, get the answer

An agentic Text-to-SQL assistant built as a stateful LangGraph workflow: schema retrieval, SQL generation, validation, execution, error-driven retry and answer synthesis. Read-only access and SQL safety checks protect production data.

LangGraph, LangChain, OpenAI GPT, MySQL, SQLAlchemy, FastAPI, Docker

No more console browsing

Users ask about chemical prices in natural language and get answers with follow-ups. Benchmarked for accuracy, latency and cost.

Tenet Medcorp

Patient Diagnostic Assistant

A RAG assistant on WhatsApp and web, grounded in medical knowledge bases and patient history, deployed in Docker on AWS for low-latency answers.

40% fewer queries

1,000+ patients served. Escalations to human support down about 35%.

LangChain, OpenAI GPT, FAISS, Pinecone, Twilio WhatsApp API, FastAPI, AWS

Tenet Medcorp

Radiology Report Drafting

Converts structured radiologist findings into standardized reports with clinical-terminology-aware prompts, plus OpenCV preprocessing of scanned images for multimodal analysis.

50% faster drafting

90%+ radiologist approval across 100+ scans a day.

Azure OpenAI, SpaCy, Hugging Face, OpenCV, FastAPI, MLflow

Tenet Medcorp

Lab Report Summarization

An OCR, OpenCV and LLM pipeline that writes patient-friendly summaries and flags abnormal biomarkers for clinician review.

10 minutes to under 3

500+ scanned and digital reports processed every day.

Tesseract OCR, OpenCV, SpaCy, NLTK, LLM integration, FastAPI

Tenet Medcorp

Disease Risk Prediction Model

A predictive model on 10,000+ patient records. I compared logistic regression, random forest and XGBoost, then tuned features and hyperparameters.

15% better accuracy

Outputs feed proactive outreach and early intervention.

Scikit-Learn, XGBoost, Pandas, NumPy, Jupyter

Where I work and what I use

Production AI in industrial data and healthcare. Every system is evaluated for accuracy, cost, latency and safety.

September 2026 to present

AI/ML Engineer, ChemAnalyst

Built the LangGraph conversational SQL agent with a self-correction loop, served through FastAPI, and work with analysts and engineers to take GenAI features to production.

August 2022 to August 2026, Hyderabad

Data Scientist, Tenet Medcorp Pvt Ltd

RAG applications, LoRA fine-tuned LLMs, multimodal pipelines, ML models and MLflow-based MLOps for healthcare, shipped with clinical and engineering teams.

Education

B.Tech, Computer Science and Engineering

Sree Chaitanya College of Engineering, JNTUH. Master's Program in AI and Machine Learning including Generative AI.

LLM agents and RAG

LangGraph, LangChain, OpenAI, Azure OpenAI, tool calling, structured outputs, guardrails, prompt engineering, LoRA/PEFT fine-tuning.

Retrieval

FAISS, Pinecone, Qdrant, ChromaDB.

Machine learning

Scikit-Learn, XGBoost, PyTorch, TensorFlow, OpenCV, OCR.

Delivery

Python, SQL, FastAPI, Docker, MLflow, AWS (Lambda, SageMaker), CI/CD, Git.

How we work together

A simple process with a clear success metric from day one.

  1. You email me the problem, data and deadline.
  2. We agree scope, cost and a success metric.
  3. I build and test, tracking accuracy, latency and cost.
  4. I deploy and hand over with documentation.

Questions

Short answers before you get in touch.

Who is Saicharan Pittala?

Saicharan Pittala is an AI and Machine Learning Engineer based in Hyderabad, India, with 4+ years of experience building LLM agents, RAG systems, Text-to-SQL solutions, Fine Tuning & Quantization and machine learning models.

Is Saicharan Pittala available for freelance AI and ML work?

Yes. Saicharan Pittala is open to freelance AI and ML projects. Email saicharanpittala01@gmail.com with the problem, data and timeline.

What AI and ML services does Saicharan Pittala offer?

RAG and document Q&A, AI agents and Text-to-SQL with LangGraph, LLM fine-tuning with LoRA and PEFT, document AI with OCR, predictive ML models, and deployment with FastAPI, Docker and AWS or Azure.

How can I contact Saicharan Pittala?

By email at saicharanpittala01@gmail.com.

Have a project in mind?

Tell me what you are building, your timeline and any data constraints. I reply to every serious enquiry.

saicharanpittala01@gmail.com