Generative AI Engineer
Training Basket (company site, opens in a new tab)NoidaOn-siteDirect career pageEst. 12–30 LPA
Posted 6d ago
Reach people at Training Basket
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Training Basket you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Build and deploy LLM-powered applications, including chatbots, virtual assistants, and automation workflows.
- Own RAG pipelines and supporting components such as vector search, prompt design, model evaluation, testing, and monitoring.
- Improve response accuracy, latency, and cost while addressing data privacy and responsible AI requirements.
Minimum Requirements
- Work Experience Required: Not explicitly mentioned in the JD; hands-on experience with Generative AI and LLMs is required.
- Strong Python programming; knowledge of prompt and context engineering, RAG, NLP, embeddings, semantic search, and ML/deep learning fundamentals.
- Experience with an LLM API or model platform (OpenAI, Gemini, Claude, or Hugging Face), LangChain or LlamaIndex, and a vector database (Pinecone, FAISS, ChromaDB, or Weaviate).
- REST API experience and FastAPI or Flask; familiarity with Git, Docker, and AWS, Azure, or GCP.
Ideal Candidate Profile
- Has practical experience taking LLM applications from development through deployment and evaluation, rather than only experimenting with prompts.
- Can build end-to-end RAG solutions, connecting model APIs, embeddings, vector search, and application interfaces.
- Fits work involving cross-functional delivery with software engineering, data science, and product teams, while balancing quality, latency, cost, privacy, and security.
