The Applied AI Engineer will design, develop, evaluate, and deploy scalable, enterprise-grade generative AI solutions. The role emphasizes agentic workflows, LLM evaluation, RAG using knowledge and vector bases, and MLOps implementation using AWS Bedrock and SageMaker.
Key Responsibilities
- Design and deploy AI agents, agentic workflows, and enterprise generative AI applications.
- Develop, fine-tune, and evaluate LLMs, including Claude, Azure OpenAI, and open-weight models.
- Build RAG solutions using vector databases, graph databases, and enterprise knowledge bases.
- Implement MCP and Agent-to-Agent (A2A) communication.
- Develop AI and ML workflows using AWS SageMaker and Bedrock, along with MLflow and Kubeflow on Kubernetes and EKS.
- Create data ingestion, embedding, and multimodal processing pipelines using Python, Spark, and PySpark.
- Integrate AI solutions with enterprise platforms through APIs and standardized architectural patterns.
- Implement LLM evaluation, trace evaluation, safety guardrails, and validation frameworks such as DeepEval.
- Apply CI/CD, Git, Spec-Based Development, and cloud-native engineering best practices.
Required Qualifications
- Bachelor's degree in Computer Science, Data Science, AI/ML, or related field; Master's preferred.
- Strong proficiency in Python, Pandas, NumPy, and machine learning frameworks such as Transformers and LangChain.
- Hands-on experience with generative AI, LLMs, prompt engineering, fine-tuning, and AI agent development.
- Experience with AWS, Azure OpenAI, AWS Bedrock, and SageMaker.
- Expertise in RAG architectures, vector databases, knowledge bases, and multimodal AI.
- Experience with LLM evaluation frameworks such as DeepEval and AI safety or guardrails.
- Knowledge of Git, CI/CD, Spec-Based Development, and cloud-native architectures.
- Familiarity with big data technologies such as Spark and Hadoop.
- Strong collaboration skills and experience working in Agile environments.
- GitHub code repository link required for all candidates; thorough technical vetting is mandatory.
Technology Stack
- Generative AI, LLMs, Claude, Azure OpenAI, open-weight models
- MCP, Agent-to-Agent (A2A)
- AWS SageMaker, AWS Bedrock, MLflow, Kubeflow, Kubernetes, EKS
- Python, Spark, PySpark
- Vector databases, graph databases
- DeepEval, Transformers, LangChain
- Git, CI/CD, Spec-Based Development
- AWS, Azure
Preferred Qualifications
- Experience in financial services, regulatory technology, or enterprise automation.
- Familiarity with MLOps tools such as MLflow, Kubeflow, and Weights & Biases.
- Experience with Docker, Kubernetes, and Apache Spark.
- Contributions to open-source AI projects or research publications.
- Experience with graph databases and production-grade AI deployments.
Work Location and Environment
On-site role in McLean, VA, working in a collaborative, cross-functional Agile environment.