GenAI Engineer

Key Responsibilities:

• Fine-tune and deploy LLMs (e.g., GPT, LLaMA, Mistral) using frameworks like Hugging Face Transformers and LangChain.
• Build and optimize RAG pipelines with vector databases (e.g., Pinecone, FAISS, Weaviate).
• Engineer prompts for structured and reliable outputs across diverse use cases such as chatbots, summarization tools, and coding assistants.
• Implement scalable inference pipelines; optimize for latency, throughput, and cost using quantization, distillation, and other model optimization techniques.
• Collaborate with product, design, and engineering teams to integrate generative AI capabilities into user-facing features.
• Monitor and improve model performance, accuracy, safety, and compliance in production.
• Ensure responsible AI practices through content filtering, output sanitization, and ethical deployment.

Required Skills:

• Proficiency in Python and familiarity with modern machine learning tools and libraries.
• Hands-on experience with LLM development using Hugging Face Transformers, LangChain, or LlamaIndex.
• Experience building and deploying RAG pipelines, including managing embeddings and vector search.
• Strong understanding of transformer architectures, tokenization, and prompt engineering techniques.
• Comfortable working with LLM APIs (e.g., OpenAI, Anthropic, Cohere) and serving models with FastAPI, Flask, or similar frameworks.
• Familiarity with deploying ML systems using Docker, Kubernetes, and cloud services (AWS, GCP, Azure).
• Experience with model evaluation, logging, and inference pipeline troubleshooting.

Nice to Have:

• Exposure to multimodal models (e.g., text-to-image, video generation, TTS).
• Experience with reinforcement learning from human feedback (RLHF) or alignment techniques.
• Familiarity with open-source LLMs (e.g., Mistral, Mixtral, LLaMA, Falcon) and optimization tools (LoRA, quantization, PEFT).
• Knowledge of LangChain agents, tool integration, and memory management.
• Contributions to open-source GenAI projects, public demos, or blogs in the generative AI space.
• Basic proficiency in frontend development (e.g., React, Next.js) for rapid prototyping.