Key Responsibilities
Research and implement Generative AI use cases using LLMs
(text, voice, image, or multimodal).
Build prototypes using frameworks such as LangChain, LlamaIndex
Design and optimize prompts for accuracy, safety, and
performance.
Implement RAG (Retrieval‑Augmented Generation) pipelines
using vector databases.
Integrate AI models via APIs or open‑source models (OpenAI, Azure
OpenAI, Hugging Face, local LLMs).
Work on AI agents, tools, and orchestrations (function
calling, workflows).
Evaluate model outputs using metrics like relevance, hallucination
rate, latency, and cost.
Assist in deploying GenAI applications using Docker and cloud
platforms preferably Azure.
Collaborate with product, data, and engineering teams
Document experiments, findings, and best practices.
Mentor engineers and drive best practices

Requirements
Required




Skills
3+ years of professional experience and 2+ years of experience in
GenAI.
Robust experience in Python or Java
Hands-on with LLMs, prompt engineering, and RAG
Experience with LangChain, LlamaIndex, or similar
Knowledge of vector databases (FAISS, Pinecone, etc.)
Experience with cloud platforms (Azure preferred)
Understanding of microservices and distributed systems
Basic experience with Git and REST APIs.

Ability
to read research blogs or documentation and implement ideas quickly.

Advantages
Benefits
Hands‑on exposure to contemporary GenAI stacks
Certificate / Letter of Recommendation
Access to real‑world datasets and use cases

📌 Staff Software Engineer Secunderabad (India)
🏢 Kshema
📍 India