E
EXL
AI Engineer
Gen AI Engineer
On-siteMidAI EngineerJust posted
Role summaryAI-generated
This Gen AI Engineer will build and deploy large language model applications, including RAG pipelines and agent-based systems, using tools such as LangChain and LlamaIndex. The role requires Python API development, prompt engineering, and cloud deployment on Azure, AWS, or GCP.
Skills required
About this role
- Develop GenAI applications using LLMs (OpenAI, LLaMA, etc.)
- Build RAG pipelines and agent-based systems (LangChain, LlamaIndex)
- Design prompts, optimize outputs, and implement guardrails
- Integrate AI models into APIs and production systems
- Deploy solutions on cloud (Azure/AWS/GCP)
Responsibilities
- Develop GenAI applications using LLMs (OpenAI, LLaMA, etc.)
- Build RAG pipelines and agent-based systems (LangChain, LlamaIndex)
- Design prompts, optimize outputs, and implement guardrails
- Integrate AI models into APIs and production systems
- Deploy solutions on cloud (Azure/AWS/GCP)
Qualifications
- Strong Python + API development
- Experience with LLMs, embeddings, vector DBs (FAISS, Pinecone)
- Knowledge of NLP, prompt engineering, and GenAI frameworks
Apply on EXL →Opens in new tab
score your resume against this role
