- Generative Models (e.g., GPT, LLaMA, Claude, Stable Diffusion) for text, image, audio, or video generation.

- Design and build end-to-end GenAI pipelines, from data collection and preprocessing to model training, evaluation, and deployment.

- Integrate LLMs and multimodal AI models into production systems using frameworks like LangChain, LlamaIndex, or OpenAI APIs.

- Conduct RAG (Retrieval-Augmented Generation) implementations for enterprise use cases.

- Collaborate with cross-functional teams (data science, product, and engineering) to design intelligent AI-driven applications.

- Optimize model inference, cost efficiency & response latency.

- Solid knowledge of Python and ML frameworks such as PyTorch or TensorFlow.

- Experience with LLMs (e.g., OpenAI, Anthropic, Mistral, LLaMA)



and open-source libraries (LangChain, Hugging Face Transformers, etc.).

- Understanding of prompt engineering, embeddings, vector databases (e.g., FAISS, Pinecone, Weaviate, Milvus).

- Familiarity with cloud platforms (AWS, Azure, or GCP) and MLOps best practices.

- Experience with diffusion or image generation models (e.g., Stable Diffusion, Midjourney, DALL•E).

- Exposure to multimodal systems combining text, vision, and speech.

- Exposure to Azure services like Azure AI foundry, AI search etc.

- Knowledge of API development, containerization (Docker, Kubernetes) & CI/CD pipelines.

📌 Gen AI Engineer (Chennai)
🏢 Blackstraw Technologies
📍 Chennai