Senior Engineer – Local AI Agent + RAG + Hybrid
1 week ago

+ Seamless option to route harder tasks to GPT/Claude via API
End result should feel like a personal AI associate that can search my files, think, and produce real outputs — not just chat.
I'm open to your recommendations on architecture and tooling (Ollama, LangChain/LlamaIndex, vector DBs, agent frameworks etc.).
Experience with:
- local LLM hosting
- RAG / vector databases
- Python automation/tool execution
Job description
, consectetur adipiscing elit. Nullam tempor vestibulum ex, eget consequat quam pellentesque vel. Etiam congue sed elit nec elementum. Morbi diam metus, rutrum id eleifend ac, porta in lectus. Sed scelerisque a augue et ornare.
Donec lacinia nisi nec odio ultricies imperdiet.
Morbi a dolor dignissim, tristique enim et, semper lacus. Morbi laoreet sollicitudin justo eget eleifend. Donec felis augue, accumsan in dapibus a, mattis sed ligula.
Vestibulum at aliquet erat. Curabitur rhoncus urna vitae quam suscipit
, at pulvinar turpis lacinia. Mauris magna sem, dignissim finibus fermentum ac, placerat at ex. Pellentesque aliquet, lorem pulvinar mollis ornare, orci turpis fermentum urna, non ullamcorper ligula enim a ante. Duis dolor est, consectetur ut sapien lacinia, tempor condimentum purus.
Access all high-level positions and get the job of your dreams.
Similar jobs
I'm looking for help building a private self-hosted AI assistant that runs primarily on my local machine but can use frontier cloud models when deeper reasoning is needed. · ...
The purpose of this project is to learn deployment process from your video/document/python code. · Use Azure hybrid AI search instead of direct use openai embeddings calculation and using python for best chunks search.All deployment done from browser – no remote local computer co ...
The purpose of this project is to learn the deployment process from video/document/python code. · i need Azure Container Apps with autoscaling : KEDA-based scaling in Azure Container Apps · use Free Azure AI search resources since our data is small , so use Free Azure AI search i ...
The purpose of this project is to learn deployment process from your video/document/python code. Use Free Azure AI search resources since our data is small , so use data is small enough to fit use Free Azure AI search instance. · Use persistent Chroma hosted on cloud on external ...
+The purpose of this project is to learn the deployment process from your video/document/python code. · ++Use Azure hybrid AI search instead of direct use openai embeddings calculation and using python for best chunks search. · Create Docker on azure , not on local computer. · Up ...
Job summary: · Azure architecture for backend autoscaling Postgres Python RAG azure AI hybrid search with anti spam bots. The project involves learning deployment process from video/document/python code and using Azure hybrid AI search instead of direct use openai embeddings calc ...
I'm looking for an experienced langflow/llm engineer to extend an already working rag system with knowledge graph layer. · ...
Senior AI
4 weeks ago
We are seeking a Senior RAG Architect with expertise in LLMs and RAG architectures. · Responsibilities include reviewing our current RAG architecture,deep-diving into legal-domain constraints, · and collaborating to validate assumptions and identify architectural gaps. · ...
AI Engineer Needed – Expert in RAG
1 month ago
We are looking for an experienced AI engineer who truly understands Retrieval-Augmented Generation (RAG) systems and can implement them end-to-end. · The test task will involve building or improving a RAG pipeline, · including data ingestion embedding retrieval · and LLM response ...
AI Architect
1 week ago
Nous recherchons un Architecte en IA ayant une solide expérience des systèmes d'IA en production, · de la transformation de données et des architectures modernes agentiques et RAG (Retrieval-Augmented Generation). · Chez Highspring vous travaillerez au cœur des transformations te ...
GEN AI Consultant
1 month ago
We are looking for an experienced Generative AI Consultant to lead the design and delivery of enterprise GenAI solutions using LLMs, RAG, and AI agents. · Identify and drive high-impact GenAI use casesDesign and deliver LLM, RAG, and agent-based solutionsLead architecture, implem ...
AI engineer to help in a RAG pipeline
1 month ago
We are looking for an AI Engineer with strong experience in Retrieval Augmented Generation (RAG) systems to design build and optimize intelligent applications that combine LLMs with structured and unstructured data. · ...
Senior RAG
3 weeks ago
We are building Juriscope,a legal research platform focused exclusively on official Gibraltar legislation,judgments,and policies. · A production RAG systemPostgres + pgvector (via Supabase)Hybrid retrieval (vector + FTS + title matching)10k+ legal documents fully ingested and chu ...
SENIOR AI Engineer for ISLAMIC Project
4 weeks ago
An EXPERT AI engineer is needed to build a complex hybrid rag retrieval system and agentic AI. · Developing algorithms and ensuring system efficiency. · ...
Senior RAG Architect
4 weeks ago
We are seeking a Senior RAG · (Retrieval-Augmented Generation) Architect. · evaluate our current RAG setup · validate design assumptions, · identify gaps or risks, · recommend improvements—particularly within · <ul style= ...
AI Automation
1 week ago
A B2B & B2C ecommerce business is looking to optimize and scale its AI automation setup. · Current AI tools solve isolated problems but fail at executing complex business use cases end-to-end finetuning LLMs for real product and revenue impact scaling automation reliably across C ...
We're building a knowledge curation platform (V.E.T.S.) that combines · RAG with domain expert refinement. · ...
GenAI Lead Developer
3 days ago
+Job summary · Design and develop efficient Python scripts for GenAI application. · +Design and develop efficient Python scripts · Demonstrate strong proficiency in Python programming language. · Collaborate with cloud platforms to build Generative AI applications. · +ol { list-s ...
+p>Job summary · We're building a real-time Language interpretation system that converts live speech into accurate output with human-interpreter-level latency. · You'll work closely with an existing team (backend, 3D animation, linguistics already in place). ...
Multi Modal AI Engineer
1 week ago
The Multi-Modal AI & Analytics Engineer is responsible for hands-on feasibility experiments and technical options around AI particularly for unstructured multi-modal content search optimization early pricing/insights models. · The role explores documents what works vs what is pro ...