Job
Description
Key Responsibilities: LLM Integration & Development: Build and fine-tune LLMs for task-specific applications using techniques like prompt engineering, retrieval-augmented generation (RAG), fine-tuning, and model adaptation. AI Agent Engineering: Design, develop, and orchestrate AI agents capable of reasoning, planning, tool use (e.g., APIs, plugins), and autonomous execution for user-defined goals. GenAI Use Case Implementation: Deliver GenAI-powered solutions such as chatbots, summarizers, document Q&A systems, assistants, and co-pilot tools using frameworks like LangChain or LlamaIndex. System Integration: Connect LLM-based agents to external tools, APIs, databases, and knowledge sources for real-time, contextualized task execution. Performance Tuning: Optimize model performance, cost-efficiency, safety, and latency using caching, batching, evaluation tools, and monitoring systems. Collaboration & Documentation: Work closely with AI researchers, product teams, and engineers to iterate quickly. Maintain well-structured, reusable, and documented codebases. Required Qualifications: 35 years of experience in AI/ML, with at least 12 years hands-on with GenAI or LLMs. Strong Python development skills and experience with ML frameworks (e.g., Hugging Face, LangChain, OpenAI API, Transformers). Familiarity with LLM orchestration, vector databases (e.g., FAISS, Pinecone, Weaviate), and embedding models. Understanding of prompt engineering, agent architectures, and conversational AI flows. Bachelor's or Master's degree in Computer Science, Artificial Intelligence, or related field. Preferred Qualifications: Experience deploying AI systems in cloud environments (AWS/GCP/Azure) or with containerized setups (Docker/Kubernetes). Familiarity with open-source LLMs (LLaMA, Mistral, Mixtral, etc.) and open-weight tuning methods (LoRA, QLoRA). Exposure to RAG pipelines, autonomous agents (e.g., Auto-GPT, BabyAGI), and multi-agent systems. Knowledge of model safety, evaluation, and compliance standards in GenAI.
