Generative AI Developer

**Knowledge of Generative AI is a must**

Job Summary

We are looking for a driven and curious Automation Engineer with hands-on experience in Large Language Models (LLMs). In this role, you’ll work on end-to-end development and deployment of LLM-based solutions, including prompt engineering, model fine-tuning, and cloud-based deployment. You’ll collaborate closely with product and engineering teams to build intelligent, scalable, and secure AI-powered systems.

Key Responsibilities

1.     Design, develop, and optimize prompt strategies for LLM-based applications.

2.     Fine-tune pre-trained models (e.g., Ollama, Gemini etc.) using custom datasets.

3.     Build and deploy LLM-powered APIs and services in cloud environments (AWS, GCP, or Azure).

4.     Integrate LLMs into applications with efficient inference and cost-aware strategies.

5.     Conduct evaluations, benchmarking, and A/B testing for LLM outputs.

6.     Collaborate on data collection, preprocessing, and feature engineering tasks.

7.     Stay up to date with the latest in GenAI research and toolchains.

Requirements

1. Strong grasp of NLP concepts, transformers, and recent LLM developments.
2. Proficiency in Python and ML frameworks (PyTorch, TensorFlow, or similar).
3. Experience with prompt engineering and prompt evaluation
4. Hands-on experience with cloud platforms (AWS/GCP/Azure), Docker, and CI/CD
5. Familiarity with APIs and SDKs of major LLM providers (e.g., OpenAI, Gemini, Anthropic).
6. Understanding of data privacy, security, and ethical considerations in AI.

Preferred Qualifications

1.     Experience with tools like LangChain, LlamaIndex, or Vector DBs (e.g.,ChromaDB, Pinecone).

2.     Exposure to Retrieval-Augmented Generation (RAG), Agentic and MCP based systems.

3.     Knowledge of MLOps best practices and ML model lifecycle management.

4.     Experience with designing Cloud Architecture for AI Based Applications.