LLMPrompt-Context Engineer – Fullstack Python (AI Agents, LangGraph, Context Engineering)
LLMPrompt-Context Engineer – Fullstack Python (AI Agents, LangGraph, Context Engineering)
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
Job Description:
We are looking for a highly skilled LLM/Prompt-Context Engineer with a strong fullstack Python background to design develop and integrate intelligent systems focused on large language models (LLMs) prompt engineering and advanced context management. The engineer will architect context-rich AI solutions craft effective prompts and build agent workflows using LangGraph.
Roles and Responsibilities:
Design optimize and evaluate LLM prompts for precise reliable contextually relevant outputs.
Architect dynamic context management strategies (session memory RAG personalization).
Integrate and orchestrate LLMs within Python applications using APIs and pipelines.
Build and manage conversational and multi-agent flows with LangGraph.
Develop backend services APIs and optionally front-end interfaces for AI apps.
Collaborate with product data science and engineering teams.
Implement testing monitoring and evaluation pipelines for prompt/context optimization.
Required Skills:
Deep experience in fullstack Python (FastAPI Flask Django; SQL/NoSQL).
Demonstrated expertise in LLM prompt engineering (OpenAI Anthropic OSS models).
Strong understanding of context engineering (memory vector search retrieval strategies).
Hands-on experience deploying AI agents and LLMs in production.
Proficient with LangGraph for agent workflows.
Familiarity with cloud Docker CI/CD.
Excellent analytical and communication skills.
Preferred:
Experience fine-tuning LLMs or working with RAG pipelines.
Background in IR/search or knowledge management systems.
Open-source contributions to LLM/agent frameworks.
Employment Type
Full-time
