AI Engineer & Full-Stack Developer

I build advanced query systems & LLM pipelines that ship to production—fast.

  • • 14+ years in IT • 4+ years AI/Vector DB (pgvector, Redis, Pinecone)
  • • AWS Solutions Architect • Snowflake Core Pro
  • • Full‑stack: FastAPI, Streamlit, Next.js, WordPress
Book a CallView ProjectsLinkedInGitHub
Works with
AWSAzure AIOpenAILlamaIndexPostgreSQL/pgvectorRedis
Saravanakumar Subramani portrait

About

I’m an experienced AI Engineer and Full-Stack Developer with over 14 years in IT, including 8+ years in AI/ML and NLP. I specialize in building scalable AI applications, deploying LLM-based systems, and integrating cloud platforms like AWS and Azure. With expertise in Python, LlamaIndex, LangChain, and databases like PostgreSQL and pgvector, I deliver impactful solutions in healthcare, finance, and e-commerce domains. Certified in AWS (SAA, Developer, CCP) and Snowflake Core Pro, I focus on retrieval quality, observability, and performance in production-ready systems.

  • • 14 years overall • 8+ years AI/ML & NLP
  • • Certifications: AWS SAA, Developer, CCP • Snowflake Core Pro
  • • Stack: Python, LlamaIndex, LangChain, OpenAI, FastAPI, Streamlit, PostgreSQL/pgvector, Redis, Next.js, PyTorch, Scikit-learn, AWS Bedrock, Azure AI Services
LinkedInGitHub

Core Focus

  • • RAG on pgvector/Redis
  • • Hybrid retrieval & filters
  • • Prompt & tool orchestration
  • • Caching & evals
  • • AI Search & Indexing
  • • MLOps Pipelines

Delivery

  • • FastAPI microservices
  • • Streamlit prototypes → prod
  • • Docker & CI/CD
  • • Cloudflare, AWS/Azure
  • • Hugging Face Deployment
  • • GitHub Actions Automation

Services

Outcome‑focused engineering. No buzzwords, just shipped systems.

Advanced Query Systems (RAG)

  • • LlamaIndex on pgvector/Redis
  • • Hybrid retrieval, metadata filters

LLM Pipelines

  • • Prompts, tools, guardrails
  • • Evals, caching, observability

APIs & Microservices

  • • FastAPI, Streamlit
  • • Docker, CI/CD

Cloud & WordPress

  • • AWS/Azure, Cloudflare, Hetzner
  • • Perf & cost tuning
LlamaIndexFastAPIPostgreSQL/pgvectorRedisBedrock/OpenAIAzure AINext.js

Featured Projects

DealCloser Assist placeholder

DealCloser Assist

  • • Live cues for reps during calls; fewer context switches.
  • • Metrics: coming soon.
Next.jsFastAPILlamaIndexOpenAIpgvector
Code
Clinical Summarization placeholder

Clinical Summarization (POC)

  • • Notes → structured summaries; faster clinical review.
  • • Metrics: coming soon.
PythonBiomedBERTStreamlitPostgreSQL
Code
Appeal Letter Automation placeholder

Appeal Letter Automation

  • • Drafts consistent medical appeal letters from docs/images.
  • • Metrics: coming soon.
AWS Comprehend MedicalBedrockOpenAIS3Lambda

Deep Case Study — Clinical Summarization

  • Problem: Manual review of unstructured clinical notes is slow.
  • Approach: Extraction + rules → standardized summaries; human‑in‑the‑loop.
  • Stack: Python, BiomedBERT, Streamlit, PostgreSQL.
  • Result: Review time ↓, edits ↓, consistency ↑ (validating).

Planned metrics (to instrument):

  • • Avg. review time per case
  • • Extraction coverage (% fields filled)
  • • Manual edits per summary
  • • Clinician agreement rate (spot‑checks)

Content

Let’s Chat

Book time or drop a message. I respond quickly.

LinkedInGitHub