GenAI Engineer

Job Title: GenAI Engineer
Experience: 4–8 Years
Location: Remote / Hybrid / On-site
Employment Type: Full-Time

Job Summary

We are looking for a hands-on Generative AI Engineer to design, develop, and deploy production-grade AI applications using Large Language Models (LLMs), RAG, Agentic AI, and AI orchestration frameworks. The ideal candidate should have strong Python/software engineering skills and experience integrating GenAI solutions with enterprise applications and cloud platforms.

Current enterprise GenAI roles commonly emphasize Python, RAG, vector databases, LangChain/LangGraph, LLM APIs, cloud deployment, evaluation, and responsible AI.

Key Responsibilities

• Design and develop enterprise Generative AI and LLM-powered applications.
• Build end-to-end RAG pipelines, including document ingestion, chunking, embeddings, retrieval, reranking, and response generation.
• Develop AI agents and agentic workflows using LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar frameworks.
• Integrate LLMs such as OpenAI, Azure OpenAI, Anthropic Claude, Gemini, Llama, and Mistral.
• Develop effective prompt engineering, function calling, structured outputs, and tool-use strategies.
• Work with vector databases such as Pinecone, FAISS, Chroma, Weaviate, Milvus, pgvector, or Azure AI Search.
• Develop scalable AI services and REST APIs using Python, FastAPI, or Flask.
• Fine-tune or adapt LLMs using techniques such as LoRA/QLoRA when required.
• Implement LLM evaluation for accuracy, relevance, groundedness, hallucination, latency, and cost.
• Deploy GenAI applications on AWS, Azure, or Google Cloud Platform.
• Containerize applications using Docker and support Kubernetes/CI/CD-based deployments.
• Implement security controls, guardrails, PII protection, prompt-injection prevention, and responsible AI practices.
• Monitor production AI applications and optimize model performance, scalability, reliability, and cost.
• Collaborate with product, data, software engineering, and business teams to convert use cases into production-ready AI solutions.