Note: The job is a remote job and is open to candidates in USA. The hiring company is confidential. The Generative AI Engineer designs, develops, and deploys AI-powered applications using LLMs, RAG, vector databases, and modern AI frameworks, and collaborates with cross-functional stakeholders to deliver production AI solutions.
Responsibilities
- Design, develop, and deploy Generative AI applications using LLMs such as GPT, Claude, Gemini, and open-source models
- Build and optimize RAG pipelines, including document ingestion, chunking, embedding generation, retrieval, reranking, and response generation
- Develop AI agents and multi-agent workflows using frameworks such as LangChain, LangGraph, or Semantic Kernel
- Integrate vector databases such as Pinecone, FAISS, Chroma, or Weaviate
- Implement prompt engineering, context management, and model evaluation techniques to improve response quality
- Develop REST APIs and backend services using Python and frameworks such as FastAPI or Flask
- Work with structured and unstructured data, including PDFs, documents, databases, and enterprise knowledge bases
- Implement responsible AI practices, including guardrails, hallucination mitigation, security, and data privacy
- Optimize model performance, latency, token consumption, and inference costs
- Deploy and monitor AI applications using cloud platforms and MLOps/LLMOps practices
- Collaborate with data scientists, software engineers, product managers, and business stakeholders
Skills
- Strong programming experience in Python
- Hands-on experience building Generative AI applications using commercial or open-source LLMs
- Strong understanding of LLM architecture, transformer models, tokenization, embeddings, and context windows
- Practical experience implementing RAG-based applications
- Experience with prompt engineering, few-shot learning, and structured output generation
- Familiarity with vector databases and semantic search
- Experience with APIs, microservices, and backend development
- Knowledge of NLP, machine learning, and deep learning fundamentals
- Familiarity with Git, Docker, CI/CD, and software development best practices
- Experience with at least one cloud platform: AWS, Azure, or Google Cloud
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Information Technology, or a related field, or equivalent practical experience
- Experience building AI agents, tool-calling workflows, and multi-step reasoning applications
- Familiarity with LangChain, LangGraph, LlamaIndex, or Semantic Kernel
- Experience with fine-tuning, LoRA/QLoRA, or parameter-efficient model adaptation
- Knowledge of LLM evaluation frameworks and observability tools
- Experience with Hugging Face Transformers, PyTorch, or TensorFlow
- Familiarity with Kubernetes, MLflow, and production model-serving systems
- Experience implementing AI safety, access controls, and enterprise-grade security
Benefits
- Hybrid / Remote / On-site
Company Overview