About the role
- Develop and maintain Generative AI applications using Python and LLM APIs.
- Build and enhance RAG pipelines using embeddings, vector databases, retrieval, and contextual generation.
- Develop backend services and APIs using Python, FastAPI, and REST APIs.
- Integrate LLM providers such as OpenAI, Azure OpenAI, Anthropic, and Gemini.
- Implement prompt engineering techniques for reliable and consistent LLM responses.
- Develop basic AI-agent and tool-calling workflows under the guidance of senior engineers.
- Work with vector databases for semantic search and knowledge retrieval.
- Design and implement database integrations using PostgreSQL.
- Write reusable, maintainable, and well-tested Python code.
- Containerize applications using Docker and support cloud deployment.
- Troubleshoot API, LLM, RAG, and application-level issues.
- Participate in code reviews, technical discussions, testing, and documentation.
- Work with the Senior Engineer and AI Architect to implement technical designs and AI workflows.
- Perform POCs and evaluate new GenAI technologies when required.
- Monitor and improve application performance, reliability, response quality, and LLM usage costs.
- Python — strong hands-on experience
- FastAPI
- REST API development
- Experience developing backend applications
- Understanding of API authentication, error handling, and integration
- Understanding of Generative AI and LLMs
- Experience working with LLM APIs
- Prompt engineering
- Understanding of tokens, context windows, temperature, embeddings, etc.
- Experience with one or more LLM providers such as:
- OpenAI
- Azure OpenAI
- Anthropic
- Google Gemini
- Practical experience with Retrieval-Augmented Generation (RAG)
- Embeddings
- Semantic search
- Vector databases
- Document ingestion and chunking
- Retrieval and context construction
- Basic understanding of RAG quality and hallucination issues
- PostgreSQL
- Git / GitHub / Azure Repos
- Docker
- Basic Azure or AWS experience
- LangChain
- LangGraph
- Neo4j / GraphRAG
- Model Context Protocol (MCP)
- Ollama
- Open-source LLMs
- Azure OpenAI
- React / Next.js
- Redis
- CI/CD
- Azure DevOps / GitHub Actions
- Basic understanding of LLM evaluation and AI guardrails
- Creating a FastAPI service for an LLM application.
- Integrating an LLM API into an existing application.
- Building a basic RAG pipeline from document ingestion to response generation.
- Creating embeddings and storing/searching them in a vector database.
- Implementing prompt templates and structured LLM responses.
- Building basic tool-calling or agent workflows.
- Connecting AI services with PostgreSQL and other backend systems.
- Dockerizing a Python application.
- Debugging API and LLM integration issues.
- Writing unit tests and maintaining clean Git-based development practices.
- Strong software development fundamentals with practical Python experience.
- Genuine hands-on experience building GenAI applications, not just theoretical knowledge.
- Good understanding of RAG concepts and LLM application patterns.
- Ability to learn new AI frameworks and technologies quickly.
- Good debugging and problem-solving skills.
- Ability to work effectively under the guidance of a Senior Engineer and AI Architect.
- Good communication and collaboration skills.
- Willingness to work on both AI/ML and backend engineering tasks.