Description

You will develop AI-powered backend services and integrations, focusing on reliable LLM interaction and data connectivity.

This role is on-site.

Responsibilities

• Build and maintain backend services using Java (Spring Boot) or Python (FastAPI/Flask).
• Integrate Large Language Models via APIs, implementing chat completions, function calling, and structured outputs.
• Develop and iterate on prompts to ensure consistent, high-quality model responses.
• Connect applications to relational databases (SQL) and external REST APIs.
• Implement secure, maintainable code with proper version control and testing practices.

Required Skills

• 7+ years of professional software engineering experience.
• Strong proficiency in Java with Spring Boot or Python with FastAPI/Flask.
• Hands-on experience with LLM APIs, specifically OpenAI (chat, embeddings, JSON outputs).
• Practical prompt engineering skills for reliable output generation.
• Solid understanding of RESTful API design, JSON, and SQL.
• Experience with Git, testing frameworks, and writing maintainable code.
• Strong problem-solving abilities and communication skills for working with non-technical stakeholders.
• Bachelor’s degree in Computer Science, Engineering, or equivalent experience.

Preferred Skills

• Familiarity with LLM orchestration libraries such as Spring AI, LangChain, or LlamaIndex.
• Experience with AI observability and evaluation tooling (Langfuse, LangSmith).
• Knowledge of cloud platforms (Azure/AWS/GCP), Docker, and CI/CD pipelines.

Key Skills

Education

Any Graduate