> Markdown version of [/jobs/ext/4418992-llm-application-engineer](https://www.wearedevelopers.com/jobs/ext/4418992-llm-application-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# LLM Application Engineer

- **Company:** SGA Inc.
- **Location:** San Francisco, CA, United States
- **Salary:** $120,000.0 - $205,000.0
- **Contract:** Permanent contract
- **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Computing Platforms, Automated Storage and Retrieval Systems, Databases, Distributed Systems, Memory Management, Python (Programming Language), Open Source Technology, OpenAI, Tensorflow, Search Technologies, Software Engineering, Pytorch, Large Language Models, Multi-Agent Systems, Prompt Engineering, Generative AI, Backend, Agentic-AI, Production Code, Machine Learning Operations
- **Published:** October 31, 2026
- **Apply:** https://www.juju.com/job/15_706413e4

## About the Role

* Strong software engineering background with experience building production-grade AI applications.
 * Hands-on experience with large language models, generative AI technologies, or autonomous agent architectures.
 * Proficiency in Python development.
 * Experience designing prompts, workflows, evaluation frameworks, and AI behavior optimization strategies.
 * Knowledge of LLM platforms, model APIs, and open-source model ecosystems.
 * Ability to develop clean, maintainable, and scalable production code.
 * Experience working across multiple layers of AI solutions, including models, systems, and end-user applications.
 * Strong analytical and problem-solving capabilities in fast-paced and evolving environments.

Preferred Skills:

 * Experience with AI orchestration frameworks and agent development platforms.
 * Knowledge of vector databases, retrieval systems, and semantic search technologies.
 * Experience building backend services, APIs, and distributed systems.
 * Familiarity with machine learning frameworks such as PyTorch or JAX.
 * Demonstrated success in iterative product development and continuous improvement initiatives.

Tech Stack

 * Python
 * LLM APIs and model providers, including OpenAI-compatible APIs and open-weight models
 * Agent frameworks and orchestration systems
 * Vector databases and retrieval systems
 * Backend services, APIs, and distributed systems
 * PyTorch / JAX

## Description

* Design, develop, and deploy applications powered by large language models and intelligent workflow automation.
 * Create agent-based systems that support reasoning, planning, memory management, tool integration, and multi-step task execution.
 * Build orchestration frameworks that transform AI-generated outputs into dependable, observable, and secure business processes.
 * Integrate AI solutions with APIs, databases, search platforms, internal services, and third-party systems.
 * Implement prompt engineering, context management, structured responses, and tool-calling techniques to improve model performance.
 * Develop evaluation methodologies, benchmarks, and datasets to monitor quality, accuracy, and regression risks.
 * Troubleshoot issues across the AI stack, including model behavior, orchestration layers, backend systems, and user experience components.
 * Optimize solutions for performance, scalability, response times, and operational cost.
 * Partner with product and engineering stakeholders to convert business requirements into practical AI-driven solutions.
 * Establish best practices for monitoring, experimentation, traceability, and continuous improvement of production AI systems.