Automation & AI Engineer

Responsibilities

• Modernize GMF and related legacy workloads by refactoring monoliths and batch processes into secure, cloud-native architectures using microservices, APIs, and event-driven systems with embedded AI and automation.
• Design, build, and deploy LLM- and agentic AI–based solutions (including LangChain, LangGraph, RAG, vector search, and AWS Bedrock agents) to automate complex workflows and integrate with IRS data sources.
• Implement platform engineering and MLOps/AIOps best practices, including CI/CD, infrastructure-as-code, model/prompt lifecycle management, and responsible AI controls.
• Partner with architects, developers, testers, and stakeholders to deliver scalable and secure AI-driven modernization solutions.
• Integrate legacy data sources into modern data platforms and AI-enabled services.
• Support compliance with security, privacy, and governance needs in a regulated federal financial environment.

Requirements

• Bachelor’s degree in Computer Science, Engineering, Data Science, or related field.
• Ability to obtain and maintain a public trust requiring U.S. Citizenship or Green Card.
• 9+ years in software, ML, or data engineering, including experience with application modernization.
• 4+ years building and deploying AI/ML or LLM-based applications in production.
• Strong experience with modern application architectures (microservices, REST APIs, event-driven) and legacy integration.
• Hands-on experience building agentic AI solutions using LLM frameworks such as LangChain and LangGraph.
• Proficiency in Python and common ML/NLP libraries including Hugging Face, Transformers, scikit-learn, and PyTorch/TensorFlow.
• Production experience with AWS services including networking/IAM, Lambda, ECS/EKS, API Gateway, S3, DynamoDB, RDS, OpenSearch, SageMaker, and CloudWatch.
• Practical experience using AWS Bedrock for LLM applications and agents (including knowledge bases and guardrails).
• Experience implementing RAG and working with vector search (vector databases/search systems).
• Experience with CI/CD and infrastructure-as-code such as Terraform or CloudFormation.
• Familiarity with MLOps/AIOps (for example, MLflow and SageMaker) and AI-focused observability including logging, metrics, and drift/quality monitoring for LLM/agent workflows.
• Strong SQL skills and experience integrating legacy data into modern platforms.
• Experience with Docker and container orchestration (Kubernetes, AWS ECS/EKS).

Technologies

Python, Hugging Face, Transformers, scikit-learn, PyTorch, TensorFlow, AWS, AWS Bedrock, LangChain, LangGraph, RAG, vector search, Terraform, CloudFormation, MLflow, SageMaker, LangSmith, Databricks, CrewAI, AutoGen, Temporal, Model Context Protocol (MCP), BrainTrust, DeepEval, CI/CD, microservices, REST APIs, event-driven, Docker, Kubernetes, ECS/EKS, Lambda, API Gateway, S3, DynamoDB, RDS, OpenSearch, CloudWatch

Desired

• Strong technical judgment and communication skills, including the ability to explain AI modernization approaches to technical and business stakeholders.
• Experience with Databricks (notebooks, Delta Lake, ML/feature store) for data and ML pipelines.
• Experience with LLM/agent observability and debugging tools (for example, LangSmith or similar).
• Experience with advanced agent frameworks such as CrewAI and AutoGen, including multi-agent workflows.
• Hands-on experience operating agents in production, including safety/guardrails, performance tuning, and lifecycle management.
• Experience with durable workflow engines such as Temporal for long-running AI/automation workflows.
• Familiarity with Model Context Protocol (MCP) for tool integration and extensible agent systems.
• Experience with LLM/agent evaluation frameworks such as BrainTrust or DeepEval (or similar).