Generative AI Engineer

Generative AI Engineer Direct hire role Hybrid onsite 3 days a week in Tysons, VA We are seeking an AI Engineer to design, develop, and deploy scalable LLM-powered solutions leveraging AWS cloud services, Snowflake, and modern GenAI frameworks. This role will focus on building production-grade AI systems, optimizing LLM inference, and integrating enterprise data platforms with cutting-edge AI technologies. The ideal candidate will have a combined background in cloud engineering expertise with hands-on experience in prompt engineering, foundation models, agentic AI systems, and data pipelines within Snowflake and AWS ecosystems Key Responsibilities AI & Generative AI Development - Design, develop, and deploy LLM-powered applications and agentic AI systems in production environments. - Implement advanced prompt engineering strategies including: - Prompt chaining and multi-turn orchestration - Few-shot learning and in-context learning - Chain-of-Thought (CoT) and Tree-of-Thought (ToT) prompting - Function calling and tool use optimization - Structured output generation (JSON, XML schemas) - Build and optimize Retrieval-Augmented Generation (RAG) systems integrating Snowflake data with LLMs. - Evaluate and fine-tune foundation models via AWS Bedrock or other managed AI services. - Develop guardrails for AI systems including hallucination mitigation, grounding, and safety controls. - Implement LLMOps best practices for model lifecycle management: - Model versioning, deployment, and rollback strategies - Prompt versioning and experimentation frameworks - Monitor and observe LLM application performance using observability tools. - Evaluation frameworks for LLM outputs Cloud & Platform Engineering (AWS) Architect scalable AI solutions using AWS services such as: - Bedrock - Sagemaker – Access and fine-tune foundation models - Lambda – Serverless LLM application deployment - EC2 – GPU-accelerated inference and batch processing - Step Functions – Orchestrate complex LLM workflows and agentic pipelines - CloudWatch – Monitoring, logging, and alerting for AI systems Data Engineering & Snowflake Integration - Build and optimize data pipelines between Snowflake and AI services. - Design feature stores and embeddings pipelines using Snowflake. - Leverage Snowflake's Cortex LLM functions for in-database AI operations. - Implement vector search and semantic search capabilities. - Work with structured and unstructured enterprise data. - Ensure data quality, governance, and security. - Optimize Snowflake queries for AI workloads and cost efficiency. AI Application Development - Build APIs and backend services to operationalize AI solutions. - Integrate LLM/AI systems into internal applications, sales tools, or analytics platforms. - Implement streaming and real-time inference for low-latency AI applications. - Collaborate with stakeholders to translate use cases into production AI systems. Required Qualifications - 5+ years of experience in AI/ML, Software or Data engineering. - Proficiency in Python with solid understanding of ML fundamentals - Strong hands-on experience with AWS, APIs and microservices architecture - Experience integrating AI solutions with data systems like Snowflake. - Practical experience with prompt engineering - Experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex, Semantic Kernel, or similar - Experience with agentic frameworks (AutoGen, CrewAI, or equivalent). Preferred Qualifications - Experience building RAG pipelines in enterprise environments. - Knowledge of MLOps best practices. - Experience with vector databases and embeddings. - Familiarity with model evaluation frameworks (e.g., LLM eval metrics). - Experience implementing AI governance and responsible AI practices. - Background in sales, media, marketing analytics, or enterprise data platforms (a plus).