Experience: 5–7 Years
Title: AI Engineer
As an AI Engineer, you will build and deploy GenAI-enabled applications by integrating LLMs into real-world systems. You will work hands‑on across backend services, AI orchestration, APIs, and cloud deployments.
-
Build GenAI-powered applications (chatbots, copilots, AI assistants, AI-enabled workflows)
-
Integrate LLMs (OpenAI / Azure OpenAI / Anthropic / OSS models) into applications
-
Develop backend services using Python / FastAPI / Flask / Node.js
-
Implement RAG pipelines using vector databases and embeddings
-
Build prompt pipelines, tool calling, and multi-step LLM workflows
-
Deploy AI services on Azure / AWS / GCP
-
Monitor performance, latency, and cost of GenAI systems
-
Work closely with frontend, data, and cloud teams
-
5+ years overall experience in software / application development
-
Strong Python (mandatory)
-
Solid backend development experience (APIs, microservices)
-
Strong hands-on experience in Generative AI & LLMs
-
Experience with:
-
LangChain / LangGraph / Similar frameworks
-
Vector DBs (Pinecone, FAISS, Weaviate, pgvector)
-
Understanding of REST, authentication, and app security
-
Experience deploying applications on cloud
-
Frontend exposure (React / Angular)
-
CI/CD, Docker, Kubernetes
-
AI evaluation & observability practices
