About the role
We are looking for an AI Engineer with strong backend engineering skills to build and deploy AI-powered products and applications. This role will be 80% focused on AI/GenAI development and 20% on backend engineering. The ideal candidate should have hands-on experience building LLM-based applications, AI agents, RAG pipelines, and AI workflows, along with strong experience in developing scalable backend systems and APIs.
The core responsibilities for the job include the following:
AI Engineering - 80%:
- Design, develop, and deploy AI/GenAI-powered applications.
- Build and optimize LLM-based applications, RAG pipelines, AI agents, and agentic workflows.
- Work with frameworks such as LangChain, LangGraph, LlamaIndex, or similar.
- Integrate LLMs and AI models from providers such as OpenAI, Anthropic, or open-source models.
- Work on prompt engineering, model evaluation, context management, and improving AI application performance.
- Develop AI solutions that can be deployed and used in production environments.
- Collaborate with product and engineering teams to convert business problems into AI-powered solutions.
Backend Engineering - 20%:
- Design and develop scalable backend services and APIs.
- Build and maintain RESTful APIs and backend integrations.
- Work with databases, cloud services, and distributed systems.
- Ensure scalability, reliability, security, and performance of backend applications.
- Integrate AI services and models with existing backend systems.
Requirements:
- 4-8 years of overall software engineering experience.
- Strong programming experience in Python.
- Hands-on experience in building production-level AI/GenAI applications.
- Strong understanding of LLMs, RAG, embeddings, vector databases, and AI agents.
- Experience with LangChain, LangGraph, LlamaIndex, or similar frameworks.
- Experience integrating APIs from OpenAI, Anthropic, or open-source models.
- Good understanding of backend development, APIs, databases, and system design.
- Experience with cloud platforms such as AWS, GCP, or Azure.
- Ability to build scalable and production-ready AI applications.