AI Engineer for RAG, LLM
Budget: $25 – $50 USD
I am looking for a highly skilled Senior Engineer to join our team as a contractor to help maintain and evolve our search infrastructure. You will be responsible for a sophisticated search system that integrates OpenSearch with Large Language Models (LLMs) and AWS Lambda.
Start your cover letter by highlighting your proudest work achievements right up front.
The ideal candidate has a deep understanding of vector databases, retrieval-augmented generation (RAG), and cloud-native Python development.
Key Responsibilities:
Search Infrastructure: Manage, configure, and optimize OpenSearch clusters (specifically focusing on vector search capabilities).
LLM Integration: Develop and maintain integrations with LLMs via APIs (e.g., OpenAI, Anthropic) or AWS Bedrock.
AI Feature Development: Implement and refine RAG pipelines, prompt engineering strategies, and potentially assist in fine-tuning models.
Backend Engineering: Design and deploy serverless functions using AWS Lambda to glue search and AI components together.
Performance Tuning: Optimize retrieval latency and LLM response accuracy.
Required Skills & Experience
Languages: Expert-level proficiency in Python.
Search: Extensive experience with OpenSearch (configuration, deployment, and indexing). Knowledge of k-NN and vector search is highly preferred.
AI/ML: Proven experience with LLM concepts, specifically RAG, Prompt Engineering, and Fine-tuning.
Cloud: Strong experience with AWS, specifically AWS Lambda and AWS Bedrock.
API Design: Experience building and consuming RESTful APIs.
Preferred Qualifications:
Experience transitioning systems from traditional keyword search to hybrid or semantic search.
Familiarity with LangChain or LlamaIndex.
Strong communication skills and the ability to work independently in a fast-paced environment.
Start your cover letter by highlighting your proudest work achievements right up front.
The ideal candidate has a deep understanding of vector databases, retrieval-augmented generation (RAG), and cloud-native Python development.
Key Responsibilities:
Search Infrastructure: Manage, configure, and optimize OpenSearch clusters (specifically focusing on vector search capabilities).
LLM Integration: Develop and maintain integrations with LLMs via APIs (e.g., OpenAI, Anthropic) or AWS Bedrock.
AI Feature Development: Implement and refine RAG pipelines, prompt engineering strategies, and potentially assist in fine-tuning models.
Backend Engineering: Design and deploy serverless functions using AWS Lambda to glue search and AI components together.
Performance Tuning: Optimize retrieval latency and LLM response accuracy.
Required Skills & Experience
Languages: Expert-level proficiency in Python.
Search: Extensive experience with OpenSearch (configuration, deployment, and indexing). Knowledge of k-NN and vector search is highly preferred.
AI/ML: Proven experience with LLM concepts, specifically RAG, Prompt Engineering, and Fine-tuning.
Cloud: Strong experience with AWS, specifically AWS Lambda and AWS Bedrock.
API Design: Experience building and consuming RESTful APIs.
Preferred Qualifications:
Experience transitioning systems from traditional keyword search to hybrid or semantic search.
Familiarity with LangChain or LlamaIndex.
Strong communication skills and the ability to work independently in a fast-paced environment.