Description :

We are seeking a highly skilled Generative AI / LLM Engineer to design, develop, fine-tune, and deploy large language modelbased solutions. The ideal candidate will have strong hands-on experience with modern LLM frameworks, vector databases, and agentic AI systems, along with solid Python programming and Linux/GPU environments.

Key Responsibilities :

- Design, develop, and deploy LLM-based applications using open-source and commercial models.

- Work with Hugging Face models, LLAMA, Mistral, and OLAMA for inference and customization.

- Perform fine-tuning of LLMs for domain-specific use cases.

- Build Agentic AI workflows using OpenAI, Gemini, and other LLM providers.

- Develop RAG (Retrieval-Augmented Generation) pipelines using LangChain and LangFlow.

- Implement and optimize vector databases (FAISS) for semantic search and retrieval.

- Apply cosine similarity search and sentence embedding techniques using Sentence Transformers.

- Write clean, scalable, and efficient Python code for AI pipelines and APIs.

- Configure and optimize GPU/CUDA environments for training and inference workloads.

- Work extensively in Linux environments for deployment and performance tuning.

- Collaborate with cross-functional teams to translate business requirements into AI-driven solutions.

- Troubleshoot, optimize, and improve model performance and system scalability.

Must-Have Skills :

- 5+ years of hands-on experience in AI / Machine Learning

- Strong experience with Generative AI and Large Language Models (LLMs)

- Hands-on with Hugging Face, LLAMA, Mistral, OLAMA

- Experience with OpenAI APIs, Gemini, and Agentic AI frameworks

- Expertise in LLM fine-tuning

- Strong experience with LangChain, LangFlow

- Hands-on knowledge of FAISS / vector databases

- Experience with semantic search, cosine similarity, and sentence transformers

- Strong Python programming skills

- Experience with GPU/CUDA configuration and optimization

- Solid Linux system knowledge

Nice to Have :

- Experience with cloud platforms (AWS / Azure / GCP)

- Knowledge of MLOps, CI/CD for ML pipelines

- Experience deploying LLMs as APIs or microservices

- Exposure to distributed training or inference

- Familiarity with prompt engineering and evaluation frameworks.