Requirements :
- Minimum
2-7 years of experience
as an AI Engineer or similar positions [MANDATORY] - Strong proficiency in
Python
, including experience with relevant libraries (e.g., requests, asyncio, json, langchain, pydantic) - Hands-on experience with
LLM APIs
(e.g., OpenAI, Anthropic, Cohere, Mistral, or open-source models via Hugging Face or similar platforms) - Proficient in
prompt engineering
techniques, including prompt design, refinement, and optimization for task-specific use cases - Solid understanding of
natural language processing (NLP)
concepts and how large language models operate - Experience integrating LLMs into real-world applications, such as chatbots, RAG (Retrieval-Augmented Generation), summarization tools, or custom AI agents
- Familiarity with frameworks for building LLM-powered applications, such as
LangChain
,
LlamaIndex
, or similar - Understanding of tokenization, embeddings, context windows, and prompt length limitations in LLMs
- Experience working with vector databases (e.g.,
FAISS
,
Pinecone
,
Weaviate
,
Chroma
) for semantic search or RAG use cases - Comfortable working with APIs and building backend services to support AI features
- Knowledge of software engineering best practices: version control (Git), testing, documentation, and CI/CD is a plus
- Exposure to MLOps or LLMOps concepts and tools is beneficial
- Ability to rapidly prototype, iterate, and scale LLM-based solutions efficiently
- Strong analytical thinking and problem-solving abilities
- Excellent communication and collaboration skills, with the ability to work in cross-functional teams