Programmer at Atlas Programmer at Atlas in Irvington, New York Posted in about 13 hours ago.

Type:

full-time We are seeking an experienced Programmer/Analyst with a strong focus on Generative AI and Agentic AI to design, develop, and deliver enterprise-grade AI solutions across complex business environments. The ideal candidate will bring 10+ years of technology and solution delivery experience, with deep hands-on expertise in modern Generative AI architectures, multi-agent systems, Retrieval-Augmented Generation, natural language processing, forecasting, recommendation systems, and enterprise AI integration. This individual will work closely with business stakeholders, architects, data scientists, engineers, and cross-functional technology teams to translate business needs into scalable, secure, production-ready AI capabilities. The role requires someone who can operate independently, move comfortably between business requirements and technical implementation, and take ownership of AI solutions from use-case definition through architecture, development, integration, testing, and deployment. Key Responsibilities Design and develop enterprise Generative AI and Agentic AI solutions aligned with business and technology requirements. Architect and implement multi-agent AI systems that coordinate specialized agents, workflows, tools, data sources, and enterprise applications. Build production-ready Retrieval-Augmented Generation, RAG, solutions, including document ingestion, chunking, embeddings, retrieval strategies, grounding, prompt orchestration, and response generation. Develop conversational AI and chatbot capabilities using enterprise data and approved knowledge sources. Design AI solutions supporting use cases such as forecasting, recommendation engines, intelligent search, NLP, summarization, knowledge retrieval, workflow automation, and decision support. Develop and orchestrate AI workflows using frameworks such as LangChain, LangGraph, CrewAI, and Model Context Protocol, MCP. Integrate large language models with APIs, enterprise systems, databases, tools, and business workflows. Design and implement vector search capabilities using vector databases and cloud-native AI services within AWS and/or Microsoft Azure environments. Evaluate and select appropriate LLMs, embedding models, retrieval techniques, orchestration patterns, and agent architectures based on business requirements. Translate ambiguous business problems into clearly defined AI use cases, technical requirements, solution architectures, and implementation plans. Partner with stakeholders to assess use-case feasibility, value, risks, dependencies, and implementation considerations. Develop reusable AI components, services, APIs, prompts, workflows, and integration patterns that support enterprise scalability. Implement appropriate controls for security, privacy, traceability, model governance, monitoring, and responsible AI. Establish testing and evaluation approaches for AI solutions, including retrieval quality, hallucination reduction, response accuracy, reliability, latency, and overall solution performance. Support deployment, troubleshooting, performance optimization, and ongoing enhancement of production AI applications. Document architecture, technical designs, workflows, APIs, development standards, and operational procedures. Provide technical leadership and guidance to development teams while remaining actively involved in hands-on solution delivery. Required Qualifications 10+ years of professional experience delivering technology, analytics, software engineering, AI, or enterprise application solutions across multiple business domains. Demonstrated hands-on experience delivering Generative AI and Agentic AI solutions in enterprise environments. Strong understanding of enterprise AI architecture and modern LLM application patterns. Proven experience designing and implementing multi-agent architectures and agent-based workflows. Hands-on experience with Retrieval-Augmented Generation, RAG, enterprise search, embeddings, semantic retrieval, and vector databases. Strong experience with AI orchestration frameworks such as: LangChain LangGraph CrewAI Model Context Protocol, MCP Experience developing AI solutions using cloud platforms such as AWS and/or Microsoft Azure. Experience integrating vector databases, enterprise data sources, APIs, cloud services, and LLM platforms. Strong programming experience, preferably with Python, and familiarity with modern software development practices. Experience with NLP technologies and architectures supporting conversational AI, text analysis, classification, summarization, extraction, or knowledge management. Experience designing or implementing forecasting and recommendation solutions. Strong understanding of APIs, microservices, data pipelines, application integration, and distributed system concepts. Demonstrated ability to convert business use cases into scalable technical solutions. Experience taking AI capabilities from proof of concept through production deployment. Strong analytical, problem-solving, communication, and stakeholder-management skills. Ability to work independently with minimal supervision while collaborating effectively across multidisciplinary teams. Preferred Qualifications Experience implementing AI solutions in highly regulated or complex enterprise environments. Experience with enterprise AI governance, responsible AI, data privacy, security, and model monitoring. Familiarity with LLM evaluation frameworks, observability tools, prompt management, and AI performance monitoring. Experience developing reusable AI platforms, accelerators, frameworks, or shared enterprise services. Familiarity with CI/CD, DevOps, MLOps, or LLMOps practices. Experience working with structured and unstructured enterprise data. Knowledge of knowledge graphs, hybrid search, semantic search, or advanced retrieval techniques. Experience supporting AI-enabled workflow automation and human-in-the-loop processes.