We are seeking an Full Stack Engineer to design, develop, deploy, and support AI-powered applications using modern large language model (LLM) technologies. You will work as part of a collaborative DevOps team, delivering production-ready solutions while contributing to automation, continuous improvement, and operational excellence.
Responsibilities
Design, develop, test, deploy, and support AI applications throughout the software development lifecycle.
Build LLM-based solutions, including AI agents, Retrieval-Augmented Generation (RAG), and multi-step workflows.
Develop and integrate RESTful APIs and backend services.
Collaborate with cross-functional teams to deliver business requirements using iterative development.
Support production systems, troubleshoot issues, and contribute to continuous improvement.
Identify and address technical debt while delivering new functionality.
Write automated unit tests and contribute to CI/CD and DevOps practices.
Participate in code reviews, knowledge sharing, and team collaboration.
Required Qualifications:
3+ years of software engineering experience.
Strong Python development skills.
Experience with LLM application development, including AI agents, RAG, prompt engineering, and tool/function calling.
Experience with LangChain, LangGraph, or similar LLM orchestration frameworks.
Strong SQL skills and experience designing RESTful APIs.
Experience with cloud-based LLM platforms (e.G., Azure OpenAI or equivalent).
Familiarity with LLM observability tools such as LangFuse or LangSmith.
Strong analytical and problem-solving skills.
Experience writing unit tests and supporting production applications.
Preferred Qualifications
Experience with Parquet, DuckDB, or other analytical databases.
Familiarity with LiteLLM or multi-LLM routing frameworks.
Working knowledge of Java and Unix/Linux environments.
