Skip to main content

Loading...

47% OFFYearly Pro

$30/mo$16/mobilled yearlyGet Pro

47% OFFYearly Pro$30/mo$16/mobilled yearlyGet Pro

Pricing

Log in Start learning free

Theme

Start learning free Log in

Sunil Samson Suresh

Sunil Samson Suresh

Author

Sr. Data Scientist at ValueMomentum · Databricks certified

I have spent my career in the applied data science trenches, building ML and NLP systems that ship. Senior Data Scientist at ValueMomentum, Databricks certified, with production experience across deep learning, LLMs, NLP, and GenAI on Azure.

Background

I have spent my career in the applied data science trenches, building ML and NLP systems that ship. Senior Data Scientist at ValueMomentum, Databricks certified, with production experience across deep learning, LLMs, NLP, and GenAI on Azure.

My focus on learnwithparam is the model and data layer of AI systems: choosing and evaluating embeddings, designing evaluation frameworks that actually catch regressions, data preprocessing for RAG, and the metrics that matter when you scale beyond a demo.

Everything I teach comes from real projects where the difference between a good model and a bad one was a dollar figure on a dashboard, not a benchmark score. The goal is evaluation-driven, data-first AI engineering, not leaderboard chasing.

What I cover

Specialty: Data science, ML, NLP, evaluation.

Embedding model selection and benchmarking
RAG evaluation frameworks (Ragas, custom metrics)
Data preprocessing and chunking for retrieval
LLM-as-a-judge evaluation pipelines
Vector database comparison and tuning
NLP and language model fundamentals
Feature engineering for GenAI applications
ML experiment tracking and reproducibility

Meet the team

Cofounder, AEOsome.com · Chief Mentor at learnwithparam.com

Co-founder & CTO, Faltara · Marketing AI at Wise

Sunil Samson Suresh

Sr. Data Scientist at ValueMomentum · Databricks certified

Asep Bagja Priandana

Electronic music instrument engineer · Polyglot builder

RAG Fundamentals

The data and retrieval layer

Agentic RAG Masterclass

Production RAG evaluation

Generative AI Foundations

LLM and NLP fundamentals

Evaluation and ML deep-dives

Recent articles by Sunil

LLM Engineering

Choosing the LLM judge for evaluation pipelines

How to pick the LLM that grades your LLM. The cost-quality tradeoffs, the calibration check, and why a weaker judge is sometimes the right call.

Evaluation LLM Metrics+2 more

8 min

LLM Engineering

Ground truth vs relevancy in RAG evaluation

Why ground truth and relevancy measure different things in RAG evals. When to use each, how to build both datasets, and the 2 metrics that matter most.

RAG Evaluation Metrics+2 more

9 min

LLM Engineering

Pydantic output structuring for RAG agent plans

How to use Pydantic models to force your RAG planner LLM to return structured steps. The schema, the retry loop, and why plain JSON prompts break in production.

RAG Pydantic Structured Output+2 more

8 min

LLM Engineering

Hallucination testing for RAG pipelines

How to test a RAG pipeline for hallucinations systematically. Adversarial prompts, the out-of-scope set, and the metric that catches confabulation.

RAG Evaluation LLM+2 more

8 min

LLM Engineering

Testing and evaluating RAG pipelines end to end

How to test a RAG pipeline like real software. Unit, integration, and eval tests that catch regressions before they ship. The 3-layer test strategy.

RAG Evaluation Production AI+2 more

8 min

LLM Engineering

LLM-based content filtering for RAG pipelines

How to filter irrelevant retrieved chunks with a cheap LLM call before the final answer. The prompt, the batch pattern, and the 40 percent noise reduction.

RAG LLM Data Processing+2 more

8 min

LLM Engineering

Retriever k-value tuning for RAG: the right top-k

How to pick the right k value for your RAG retriever. The 3-step tuning process, the failure modes of k=3 and k=20, and the sweet spot in between.

RAG Vector Databases Evaluation+2 more

8 min

LLM Engineering

Combining vector stores in RAG: multi-source retrieval

How to combine multiple vector stores in one RAG pipeline. The merge pattern, the deduplication rule, and when multi-source beats a single index.

RAG Vector Databases Production AI+2 more

8 min

LLM Engineering

FAISS vector stores in production RAG

How to use FAISS for production RAG. Index types, persistence, memory trade-offs, and the 4 settings that decide if FAISS beats a managed vector DB.

RAG Vector Databases Embeddings+2 more

8 min

AI Engineering in Practice

Real-time agent debugging with Langfuse traces

How to debug a live agent incident using Langfuse traces. The search patterns, the 5-minute workflow, and the post-mortem that catches the root cause.

Observability AI Agents Production AI+2 more

8 min

AI Engineering in Practice

Agent cost optimization from trace data

How to use Langfuse trace data to find where your agent burns tokens. The 4 queries, the cost-per-user view, and the 50 percent savings patterns.

Observability AI Agents Production AI+2 more

9 min

AI Engineering in Practice

Langfuse + Grafana: agentic AI monitoring

How to combine Langfuse traces with Grafana dashboards for agent monitoring. The integration, the panels, and the alerting that catches real problems.

Observability AI Agents Production AI+2 more

8 min

LLM Engineering

Automated evaluation pipelines for agentic AI systems

How to wire eval pipelines into CI so every agent change is scored automatically. The nightly job, the regression gate, and the dashboard that matters.

Evaluation AI Agents Production AI+2 more

8 min

LLM Engineering

Dynamic evaluation metric loading in Python

How to load evaluation metrics dynamically in a Python eval pipeline. The registry pattern, entry points, and the test override that makes CI fast.

Evaluation Python AI Agents+2 more

8 min

LLM Engineering

LLM judges: enforcing reasoning with explicit rationales

Why LLM judges without explicit reasoning drift, and how chain-of-thought rationales make their scores defensible. The prompt, the parser, the trust.

Evaluation LLM AI Agents+2 more

9 min

LLM Engineering

LLM-as-a-judge: production evaluation framework for agents

How to build an LLM-as-a-judge evaluation framework for agentic AI. The prompt, the rubric, the bias controls, and the loop that catches regressions.

Evaluation LLM AI Agents+2 more

9 min

LLM Engineering

Chain-of-thought reasoning in RAG: a practical guide

How to add chain-of-thought reasoning to a RAG pipeline. The prompt, the parsing, and the cases where CoT beats a straight answer by a wide margin.

RAG LLM Prompt Engineering+2 more

11 min

LLM Engineering

Choosing an embedding model for RAG

How to pick an embedding model for production RAG. The 5 criteria that matter, the benchmarks that lie, and the migration cost nobody warns you about.

RAG Embeddings LLM+2 more

11 min

LLM Engineering

RecursiveCharacterTextSplitter: a deep dive for RAG

How RecursiveCharacterTextSplitter works, why it beats naive chunking, and the separator order that makes or breaks retrieval quality.

RAG LLM Data Processing+2 more

11 min

LLM Engineering

RAGAS evaluation for RAG pipelines: a practical guide

How to use RAGAS to evaluate RAG pipelines. The 4 metrics that matter, the eval loop, and the trap that makes most RAG evals dishonest.

RAG Evaluation LLM+2 more

11 min

Join the engineers shipping production AI

Live sessions, code reviews, and a community of engineers building real systems on Skool.

Join the community

Learn

Find your path
Free Resources
Blog
Workshops
Webinars
Ebooks
All Courses
All Programs
RSS Feed

Courses by Topic

RAG Courses
AI Agent Courses
Multi-Agent Systems
LangGraph Courses
MCP Courses
Voice AI Courses
LLM Observability
Streaming LLM Apps
Prompt Engineering

By Role

AI Engineer
Backend Engineer
Frontend + AI
Data Engineer
Python
FastAPI

By Level

Beginner
Intermediate
Advanced

Programs

AI Engineer Accelerator
Backend Engineer Accelerator
AI Bootcamp
Backend Engineer Bootcamp
Fullstack Bootcamp
Production AI Masterclass
Fullstack AI Masterclass
MCP Masterclass
Voice AI Masterclass
All Programs

Featured Free

RAG Fundamentals
AI Agents Fundamentals
Agent Design Patterns
MCP Fundamentals
Generative AI Foundations
Prompt Engineering
Python for GenAI
FastAPI Fundamentals

Company

About
Pricing
FAQ
Convince Your Boss

Connect

YouTube
Skool Community

Build production AI systems with hands-on courses and live workshops.

© 2026 learnwithparam. All rights reserved.