GenAI Engineer

Job description

We are looking for a GenAI Engineer with hands-on experience in Generative AI and/or Agentic AI to design and develop enterprise-grade AI solutions. The role involves building LLM-powered applications, AI agents, RAG pipelines, and intelligent automation workflows. The ideal candidate should have strong Python development skills and experience with modern LLM/agent frameworks. You will work closely with product and engineering teams to take GenAI use cases from prototype to production.

Roles & Responsibilities

• Design, develop, and deploy Generative AI and Agentic AI applications using LLMs and modern AI frameworks.
• Build AI agents and multi-agent workflows with tool/function calling, reasoning, planning, and orchestration.
• Develop RAG-based solutions including document ingestion, chunking, embeddings, retrieval, and vector search.
• Integrate LLMs such as OpenAI, Azure OpenAI, Anthropic, Gemini, or equivalent models into enterprise applications.
• Develop and integrate LLM tools, APIs, and external services to enable agent-driven workflows.
• Implement prompt engineering, context management, structured outputs, and guardrails.
• Build scalable Python-based APIs and backend services for GenAI applications.
• Evaluate and optimize LLM applications for accuracy, latency, cost, reliability, and hallucination reduction.
• Implement observability and evaluation using tools such as LangSmith, MLflow, or equivalent.
• Collaborate with product, engineering, and business teams to translate use cases into production-ready AI solutions.
• Deploy GenAI solutions using cloud, Docker, CI/CD, and modern software engineering practices.

Requirements

• Mandatory hands-on experience in Generative AI or Agentic AI development.
• Strong programming experience in Python.
• Hands-on experience with LLMs and LLM application development.
• Experience with LangChain, LangGraph, AutoGen, CrewAI, or similar agent frameworks.
• Strong understanding of RAG architecture, embeddings, vector databases, and semantic search.
• Experience with AI agents, tool/function calling, agent orchestration, and multi-step workflows.
• Strong knowledge of prompt engineering and LLM context management.
• Experience integrating LLM APIs and third-party APIs/services.
• Experience developing REST APIs and production-grade backend services.
• Understanding of LLM evaluation, hallucination mitigation, guardrails, and responsible AI practices.
• Experience with at least one cloud platform AWS, Azure, or GCP.
• Good understanding of Git, Docker, CI/CD, testing, and software engineering best practices.

Good to Have

• Experience with multi-agent systems.
• Experience with MCP (Model Context Protocol).
• Experience with fine-tuning / LoRA / model customization.
• Experience with Azure AI / AWS Bedrock / Google Vertex AI.
• Experience with Pinecone, FAISS, Weaviate, Chroma, Milvus, or similar vector databases.
• Experience with LLM observability and evaluation frameworks.
• Experience building enterprise GenAI solutions in production.