Artificial Intelligence/Machine Learning Engineer - RAG/LLM

<p><p><b>Job Description : </b><br/><br/></p><p>- Lead RAG Architecture Design Define and implement best practices for retrieval-augmented generation systems, ensuring reliability, scalability, and low-latency performance.<br/><br/></p><p>- Full-Stack AI Development Build and optimize multi-stage pipelines using LLM orchestration frameworks (Lang Chain, LangGraph, Llama Index, or custom).<br/><br/></p><p>- Programming & Integration Develop services and APIs in Python and Golang to support AI workflows, document ingestion, and retrieval processes.<br/><br/></p><p>- Search & Retrieval Optimization Implement hybrid search, vector embeddings, and semantic ranking strategies to improve contextual accuracy.<br/><br/></p><p>- Prompt Engineering Design and iterate on few-shot, chain-of-thought, and tool-augmented prompts for domain-specific applications.<br/><br/></p><p>- Bachelor's degree required<br/><br/></p><p>- Strong proficiency in Python and Golang or RUST, with experience building high-performance services and APIs.</p><p><b><br/></b></p><p><p><b>Key Responsibilities : </b></p><p><br/></p>- Lead RAG Architecture Design Define and implement best practices for retrieval-augmented generation systems, ensuring reliability, scalability, and low-latency performance.<br/><br/></p><p>- Full-Stack AI Development Build and optimize multi-stage pipelines using LLM orchestration frameworks (LangChain, LangGraph, LlamaIndex, or custom).<br/><br/></p><p>- Programming & Integration Develop services and APIs in Python and Golang to support AI workflows, document ingestion, and retrieval processes.<br/><br/></p><p>- Search & Retrieval Optimization Implement hybrid search, vector embeddings, and semantic ranking strategies to improve contextual accuracy.<br/><br/></p><p>- Prompt Engineering Design and iterate on few-shot, chain-of-thought, and tool-augmented prompts for domain-specific applications.<br/><br/></p><p>- Mentorship & Collaboration Partner with cross-functional teams and guide engineers on RAG and LLM best practices.<br/><br/></p><p>- Performance Monitoring Establish KPIs and evaluation metrics for RAG pipeline quality and model :</b></p><p><b><br/></b></p><p><b>Must Have : </b><br/><br/></p><p>- 8+ years in software engineering or applied AI/ML, with at least 2+ years focused on LLMs and retrieval systems.<br/><br/></p><p>- <b>Strong proficiency in Python and Golang or RUST</b>, with experience building high-performance services and APIs.<br/><br/></p><p>- Expertise in RAG frameworks (Lang Chain, LangGraph, Llama Index) and embedding models.<br/><br/></p><p>- Hands-on experience with vector databases (Databricks Vector Store, Pinecone, Weaviate, Milvus, Chroma).<br/><br/></p><p>- Strong understanding of hybrid search (semantic + keyword) and embedding optimization.<br/><br/></p><p>- Bachelor's degree : </b></p><p><br/></p>- LLM fine-tuning experience (LoRA, PEFT).<br/><br/></p><p>- Knowledge graph integration with LLMs.<br/><br/></p><p>- Familiarity with cloud ML deployment (AWS (preferred), Databricks, Azure).<br/><br/></p><p>- Masters or PHD degree in CS</p><p><br/></p><p><b>Soft Skills :<br/></b><br/></p><p>- Strong problem-solving and decision-making skills under tight timelines.<br/><br/></p><p>- Excellent communication for cross-functional collaboration.<br/><br/></p><p>- Ability to work independently while aligning with strategic goals</p><br/></p> (ref:hirist.tech)