Salmon Joy

Senior AI Engineer and AI Trainer with 7+ years of experience in AI, Machine Learning, Generative AI, RAG systems, LLM deployment, Conversational AI

Joined on Oct 6, 2026

Salmon Joy

Nov 1

Workflow vs agent

#ai #architecture #machinelearning #enterprise

5 min read

Salmon Joy

Oct 29

Evidence-first generation and citations

#ai #architecture #machinelearning #enterprise

4 min read

Salmon Joy

Oct 26

Multi-hop retrieval

#ai #architecture #machinelearning #enterprise

4 min read

Salmon Joy

Oct 25

Query rewriting and HyDE

#ai #architecture #machinelearning #enterprise

4 min read

Salmon Joy

Oct 22

Two-stage retrieval and reranking

#ai #architecture #machinelearning #enterprise

5 min read

Salmon Joy

Oct 21

Hybrid search: lexical + vector

#ai #architecture #machinelearning #enterprise

5 min read

Salmon Joy

Oct 15

Managed model API vs self-hosted inference

#ai #architecture #machinelearning #enterprise

5 min read

Salmon Joy

Oct 14

Enterprise AI gateway

#ai #architecture #machinelearning #enterprise

5 min read

Salmon Joy

Oct 13

Reasoning depth vs latency vs cost

#ai #architecture #machinelearning #enterprise

6 min read

Salmon Joy

Oct 12

Prompting vs RAG vs fine-tuning

#ai #architecture #machinelearning #enterprise

5 min read

Salmon Joy

Oct 9

Long context vs RAG

#ai #architecture #machinelearning #enterprise

3 min read

Salmon Joy

Oct 8

Function calling vs free-form generation

#ai #architecture #machinelearning #enterprise

3 min read

Salmon Joy

Oct 7

Structured outputs as application contracts

#ai #architecture #machinelearning #enterprise

2 min read

Salmon Joy

Oct 6

Context engineering vs prompt engineering

#ai #architecture #machinelearning #enterprise

3 min read

Salmon Joy

Oct 6

Model selection is an architecture decision

#ai #architecture #machinelearning #enterprise

2 min read

DEV Community

Salmon Joy

Badges

Writing Debut

Workflow vs agent

Evidence-first generation and citations

Multi-hop retrieval

Query rewriting and HyDE

Two-stage retrieval and reranking

Hybrid search: lexical + vector

Managed model API vs self-hosted inference

Enterprise AI gateway

Reasoning depth vs latency vs cost

Prompting vs RAG vs fine-tuning

Long context vs RAG

Function calling vs free-form generation

Structured outputs as application contracts

Context engineering vs prompt engineering

Model selection is an architecture decision