18 Nov
|
SNDK
|
Ahmedabad
Roles and Responsibilities
Design and develop applications using large language models (LLMs).
Build Retrieval-Augmented Generation (RAG) pipelines for enterprise documents and knowledge bases.
Develop AI agents that connect with APIs, databases, and business applications.
Create and refine prompts to improve accuracy, consistency, and output quality.
Build data ingestion workflows covering extraction, chunking, embeddings, and retrieval.
Evaluate AI solutions for correctness, hallucinations, latency, and cost.
Develop backend APIs and integrate AI features into web and mobile applications.
Implement appropriate access controls, data protection, and safeguards against prompt injection.
Deploy, monitor, and maintain AI applications on cloud platforms.
Collaborate with project managers, developers, and clients to translate requirements into working solutions.
Desired Candidate Profile
Solid Python programming skills and experience building REST APIs using FastAPI or Flask.
Hands-on experience integrating LLM APIs or deploying open-source models.
Practical knowledge of RAG, embeddings, vector databases, and semantic search.
Experience with an LLM application framework such as LangChain or LlamaIndex.
Familiarity with vector stores such as FAISS, Pinecone, Qdrant, or pgvector.
Understanding of tool calling, structured outputs, and agent workflows.
Experience with SQL, Git, Docker, and cloud deployment.
Ability to debug AI pipelines and measure performance using test datasets.
Solid problem-solving, communication, and documentation skills.
📌 Generative Ai Engineer Ahmedabad
🏢 SNDK
📍 Ahmedabad