Intelligent Automation/AI-ML Engineer

Intelligent Automation/AI-ML Engineer

Location: Herndon, VA (Hybrid Work)

Preferred: US Citizenship

Experience: 3+ yrs & 5 yrs

Role Summary

The Intelligent Automation / AI-ML Engineer is the architect and guardian of intelligent automation solutions that incorporate AI/ML technologies, built on open-source AI models and the Model Context Protocol (MCP). The role ensures the operational efficiency and continuous refinement of integrated AI/ML solutions. Responsibility spans the design, maintenance and optimization of intelligent applications, as well as troubleshooting and resolving issues that arise after implementation.

The engineer also explores new ways to embed artificial intelligence and machine learning into automations to support continuous improvement, learning and augmented decision making, and builds repeatable intelligent solutions and bots for document processing, data cleansing and similar use cases. The role owns token management and optimization, model usage, performance, retraining and MLOps.

Key Responsibilities

Solution Design and Development

• Architect, design and build intelligent automation solutions that embed AI/ML capabilities using open-source models and MCP-based integrations.
• Develop MCP servers and clients that securely connect models to enterprise tools, data sources and workflows.
• Build repeatable, reusable intelligent solutions and bots for document processing (classification, extraction, summarization, validation) and data cleansing (deduplication, normalization, enrichment, anomaly detection).
• Design agentic and human-in-the-loop workflows that support augmented decision making.
• Create reusable components, templates and patterns that accelerate delivery across the organization.

Operations, Maintenance and Support

• Maintain and optimize deployed AI/ML solutions for reliability, accuracy and operational efficiency.
• Troubleshoot and resolve post-implementation issues, including model drift, integration failures, data quality problems and performance degradation.
• Monitor production solutions, define SLAs/SLOs, and perform root-cause analysis and corrective action.
• Maintain documentation, runbooks and knowledge base articles for supported solutions.

MLOps and Model Lifecycle Management

• Implement and manage MLOps pipelines covering versioning, CI/CD, automated testing, deployment, monitoring and rollback.
• Own model retraining strategy, including drift detection, data and label management, evaluation benchmarks and scheduled or triggered retraining.
• Track experiments, datasets and model artifacts using tools such as MLflow, DVC or equivalent.
• Evaluate, fine-tune and select open-source models, balancing accuracy, latency, cost and licensing.
• Establish model governance, including auditability, reproducibility, bias and safety checks, and responsible AI practices.

Token Management, Optimization and Performance

• Implement token management and usage controls, including budgets, quotas, rate limiting, caching and cost attribution by team or use case.
• Optimize prompts, context windows, retrieval strategies and model routing to reduce token consumption and cost without sacrificing quality.
• Monitor and tune model usage and performance: latency, throughput, GPU/CPU utilization, quantization, batching and inference serving.
• Produce dashboards and reports on usage, cost, quality and ROI.

Innovation and Continuous Improvement

• Explore and prototype new options for embedding AI/ML into automations to enable continuous improvement and learning.
• Evaluate emerging open-source models, frameworks, MCP capabilities and automation platforms, and recommend adoption where valuable.
• Partner with business stakeholders to identify automation opportunities, define success metrics and measure outcomes.

Security, Compliance and Collaboration

• Apply security best practices for data privacy, access control, secrets management and prompt-injection and data-leakage mitigation.
• Ensure solutions comply with organizational policies and relevant regulations.
• Collaborate with data engineers, software engineers, security teams, business analysts and process owners.
• Mentor team members and share best practices.

Requirements

Required Qualifications

• Bachelor's degree in Computer Science, Data Science, Engineering or a related field (or equivalent experience).
• Experience in AI/ML engineering, intelligent automation or software engineering, with production deployments.
• Strong Python skills and experience with ML/LLM frameworks such as PyTorch, Hugging Face Transformers, LangChain/LlamaIndex or similar.
• Hands-on experience with open-source LLMs, including deployment and inference serving and fine-tuning techniques.
• Practical experience with the Model Context Protocol (MCP) or comparable tool-integration and agent frameworks.
• Experience building document processing solutions (OCR, NLP, information extraction) and data cleansing pipelines.
• Working knowledge of MLOps practices and tools (CI/CD, containerization with Docker/Kubernetes, model registries, monitoring).
• Experience with token usage tracking, cost optimization and performance tuning of LLM applications.
• Familiarity with RAG architectures, vector databases and embeddings.
• Strong troubleshooting, analytical and communication skills.

Preferred Qualifications

• Experience with RPA or workflow platforms (e.g., UiPath, Automation Anywhere, Power Automate, n8n, Camunda).
• Cloud experience (AWS, Azure or GCP), including GPU workloads and managed ML services.
• Experience with orchestration tools (Airflow, Prefect, Kubeflow) and observability tools (Prometheus, Grafana, OpenTelemetry, LLM tracing tools).
• Knowledge of model evaluation frameworks, guardrails and responsible AI.
• Relevant certifications in cloud, ML or automation platforms.
• Experience working in an Agile/DevOps environment.