Role - LLM/Prompt-Context Engineer – Fullstack Python (AI Agents, LangGraph)
Location – 1st Atlanta, 2nd Dallas, 3rd Seattle (Onsite)
Contract
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. In this role, you will play a critical part in architecting context-rich AI solutions, crafting effective prompts, and ensuring seamless agent interactions using frameworks like LangGraph.
Key Responsibilities:
• Prompt & Context Engineering:
Design, optimize, and evaluate prompts for LLMs to achieve precise, reliable, and contextually relevant outputs across a variety of use cases.
• Context Management:
Architect and implement dynamic context management strategies, including session memory, retrieval-augmented generation, and user personalization, to enhance agent performance.
• LLM Integration:
Integrate, fine-tune, and orchestrate LLMs within Python-based applications, leveraging APIs and custom pipelines for scalable deployment.
• LangGraph & Agent Flows:
Build and manage complex conversational and agent workflows using the LangGraph framework to support multi-agent or multi-step solutions.
• Fullstack Development:
Develop robust backend services, APIs, and (optionally) front-end interfaces to enable end-to-end AI-powered applications.
• Collaboration:
Work closely with product, data science, and engineering teams to define requirements, run prompt experiments, and iterate quickly on solutions.
• Evaluation & Optimization:
Implement testing, monitoring, and evaluation pipelines to continuously improve prompt effectiveness and context handling.
Required Skills & Qualifications:
• Deep experience with fullstack Python development (FastAPI, Flask, Django; SQL/NoSQL databases).
• Demonstrated expertise in prompt engineering for LLMs (e.g., OpenAI, Anthropic, open-source LLMs).
• Strong understanding of context engineering, including session management, vector search, and knowledge retrieval strategies.
• Hands-on experience integrating AI agents and LLMs into production systems.
• Proficient with conversational flow frameworks such as LangGraph.
• Familiarity with cloud infrastructure, containerization (Docker), and CI/CD practices.
• Exceptional analytical, problem-solving, and communication skills.
Preferred:
• Experience evaluating and fine-tuning LLMs or working with RAG architectures.
• Background in information retrieval, search, or knowledge management systems.
• Contributions to open-source LLM, agent, or prompt engineering projects