AI/ML Engineer

Key Responsibilities

• Design and develop production-grade Python APIs and services.
• Deploy and operate containerized applications on OpenShift, configuring manifests, services, routes, and secrets.
• Partner with AI/ML engineers to productionize model capabilities into usable backend services.
• Integrate backend APIs with Angular-based front-end applications.
• Remediate security vulnerabilities in Python libraries, container images, and OpenShift deployment configurations.
• Design and implement advanced RAG pipelines using vector databases, embeddings, and knowledge graphs.
• Develop agentic AI systems using LangGraph for dynamic task planning, tool orchestration, and multi-agent workflows.
• Integrate Model Context Protocol (MCP) for standardized context sharing and agent communication.
• Design memory systems and contextual state management for agent continuity.
• Implement evaluation pipelines, prompt engineering strategies, and guardrails to ensure performance, safety, and reliability.
• Apply Model Risk Management (MRM) practices across the AI lifecycle, including model validation, explainability, and monitoring.

Required Qualifications

• Primary Skill: Artificial Intelligence/Machine Learning
• Secondary Skill: Python
• Tertiary Skill: Natural Language Processing
• Education: Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
• Experience:
• Proven experience deploying LLM-powered production systems.
• Hands-on experience with agentic AI frameworks, particularly LangGraph, and emerging standards such as Model Context Protocol (MCP).
• Strong experience designing and implementing advanced RAG architectures, including Graph RAG.
• Experience with LLM orchestration frameworks such as LangChain, LangGraph, and LlamaIndex.
• Hands-on experience with vector databases like FAISS, Pinecone, Weaviate, or Azure AI Search.
• Strong understanding of LLMOps/MLOps, including CI/CD, observability, monitoring, and performance optimization.
• Working knowledge of Model Risk Management (MRM) frameworks.
• Experience with model evaluation, benchmarking, and explainability tools.
• Technical Skills:
• Strong proficiency in Python programming, with experience building scalable AI/ML systems.
• Proficiency with Python ML/AI frameworks such as PyTorch, TensorFlow, and Scikit-learn.
• Deep understanding of agent orchestration patterns, including planning, reflection, tool usage, and multi-agent collaboration.
• Familiarity with AI safety and alignment techniques, including guardrails and bias mitigation.
• Proficiency with development tools such as GitHub, VS Code, and JIRA.
• Knowledge of RedHat OpenShift.
• Understanding of Natural Language Processing.

Preferred Qualifications

• Experience working in an Agile development methodology.
• Experience with Retrieval-Augmented Generation (RAG) and Large Language Models (LLM).