Hi👋I'mSarankumar S
I'm a Generative AI & ML Engineer building inference systems, agent tooling, and AI delivery pipelines at production scale
LangGraph, RAG and vLLM are my go-to stack for agents and inference
I work with AWS Bedrock, PyTorch and TypeScript for full-stack AI delivery
I am open to new opportunities. You can book a call with me here.
Featured projects
- HireScoutEvidence-backed candidate verificationnewOct
- ManiculeOpen-source markdown editorSep
- Chronicle SeedDigital time capsule for your future selfAug
- GoML Review PilotModel-agnostic code review systemMar
- RoastMyCVCandid resume analysis and scoringMay
- Job InsightATS resumes and career guidanceMay
- WeatherMate AIPersonalized weather agentJun
Recent posts
- Claude Opus 5.5 LLM testingGoML’s Opus 5.5 LLM testing covers benchmark results, critical bug fixes, missed tasks, cost, safety and deployment decisions for enterprise coding.
- Grok 4.7 LLM testing v/s enterprise realityGrok 4.7 LLM testing covers coding performance, speed, cost, data handling, and AI Matic Bench Score results for enterprise AI workloads.
- Harness Engineering for AI AgentsThe missing layer for production deployment of AI agents.
- LLM Testing of Muse Spark 1.3Putting Muse Spark 1.3 through GoML's evaluation suite to see where it lands.
- GPT 6 LLM Testing: What the Benchmarks Mean for Enterprise DeliveryWhat the GPT-6 benchmarks mean for enterprise AI delivery.
Stack
01 Languages
Python
TypeScript
02 Agents & RAG
LangGraph
MCP
RAG
GraphRAG
LlamaIndex
DSPy
03 Models & inference
PyTorch
Transformers
LoRA fine-tuning
vLLM
AWS Bedrock
04 Full stack
FastAPI
Next.js
pgvector
Hello there!
- I'm Saran. I build inference systems and agent tooling with LangGraph, RAG, and vLLM, and I ship the AI delivery pipelines around them at production scale.
- I write about what I learn from LLM testing and agent harnesses at goML to transformers explained simply on Medium.
- Right now, I'm an Applied AI Engineer at goML and always open to new opportunities and good conversations.
Socials