GenAI Engineer (US)

About the role

We are seeking a GenAI Engineer to design, develop, and deploy Generative AI applications powered by LLMs, Retrieval-Augmented Generation (RAG), Python, and LangChain. You will work across the full AI application lifecycle, from prototyping and experimentation to production deployment and optimization.

Key Responsibilities

• Design and develop production-ready Generative AI applications using LLMs.
• Build and optimize RAG pipelines for accurate, context-aware responses.
• Develop AI workflows and application components using Python and LangChain.
• Integrate commercial and open-source large language models into enterprise applications.
• Develop document ingestion, chunking, embedding, retrieval, and reranking workflows.
• Implement prompt engineering, structured outputs, tool calling, and AI agents.
• Evaluate model quality, relevance, latency, and reliability using appropriate evaluation techniques.
• Optimize applications for performance, scalability, cost, and response quality.
• Build APIs and services that integrate GenAI capabilities with existing software platforms.
• Collaborate with software engineers, data scientists, product managers, and business stakeholders.
• Monitor production AI systems and continuously improve model and application performance.
• Follow responsible AI, security, privacy, and software engineering best practices.

Required Qualifications

• 2–5 years of professional experience in software engineering, machine learning, AI engineering, or a related field.
• Strong programming experience with Python.
• Hands-on experience building applications with LLMs.
• Practical experience developing RAG-based applications.
• Experience with LangChain or similar LLM application frameworks.
• Understanding of embeddings, vector databases, semantic search, and information retrieval.
• Strong understanding of prompt engineering and LLM application architecture.
• Experience working with APIs and production software development.
• Strong debugging, analytical, and problem-solving skills.

Preferred Qualifications

• Experience with LangGraph, LlamaIndex, or similar frameworks.
• Familiarity with vector databases such as Pinecone, Weaviate, Milvus, or pgvector.
• Experience with cloud platforms such as AWS, Azure, or Google Cloud.
• Knowledge of Docker, Kubernetes, CI/CD, and MLOps practices.
• Experience with LLM evaluation, observability, guardrails, and AI safety.
• Familiarity with NLP, machine learning, or deep learning concepts.