Senior GEN AI Developer

Senior Generative AI Developer

Location: New York City, NY

Experience: 8–14 Years

Work Arrangement: Onsite / Hybrid

Employment Type: Full-Time

Job Overview

We are seeking a highly skilled Senior Generative AI Developer with 8–14 years of software engineering experience and strong hands-on expertise in Generative AI, LLMs, Agentic AI, MCP, LangGraph, LangChain, Python, and RAG .

The ideal candidate will have proven experience designing, developing, and deploying production-grade GenAI applications and intelligent AI agents.

Key Responsibilities

• Design, develop, and deploy LLM-powered Generative AI applications using Python.
• Build Agentic AI solutions capable of reasoning, planning, tool usage, and multi-step task execution.
• Develop AI agents and workflows using LangGraph and LangChain .
• Design and implement Model Context Protocol (MCP) servers, tools, and integrations.
• Build scalable RAG pipelines , including document ingestion, chunking, embeddings, retrieval, reranking, and response generation.
• Integrate LLMs such as OpenAI, Azure OpenAI, Anthropic, Google Gemini, or AWS Bedrock .
• Implement prompt engineering, function calling, tool calling, structured outputs, memory, and context management .
• Develop multi-agent workflows and autonomous AI solutions.
• Build APIs and backend services using Python/FastAPI .
• Integrate vector databases and enterprise data sources for semantic search and RAG.
• Implement LLM evaluation, observability, monitoring, and performance optimization.
• Collaborate with architects, data engineers, and product teams to deliver enterprise AI solutions.

Required Skills

• 8–14 years of overall software development experience .
• Strong hands-on Python coding/programming experience.
• Strong hands-on experience with Generative AI and LLMs .
• Proven experience developing Agentic AI / AI Agents .
• Strong experience with LangChain and LangGraph .
• Hands-on experience with MCP (Model Context Protocol) .
• Strong experience designing and implementing RAG architectures .
• Experience with embeddings, vector databases, semantic search, and retrieval techniques .
• Strong knowledge of prompt engineering, tool calling, function calling, and structured outputs .
• Experience integrating commercial or open-source LLMs.
• Strong software engineering and API development experience.

Preferred Skills

• FastAPI, REST APIs, Microservices
• Vector databases: Pinecone, FAISS, Weaviate, Milvus, Chroma
• LangSmith or other LLM evaluation/observability tools
• AWS / Azure / GCP
• Docker and Kubernetes
• CI/CD
• LLM evaluation and AI guardrails
• Multi-agent frameworks and enterprise AI integrations