Artificial Intelligence/Machine Learning Engineer

As an AI/ML Engineer on the Evergreen.AI team, you will design, build, and deploy enterprise-grade agentic AI systems for real customer production environments. This role is highly hands-on and focuses on creating scalable agent frameworks, retrieval systems, workflow orchestration, evaluation pipelines, and integrations with enterprise platforms. You will work closely with engineering, product, delivery, and data/knowledge teams to turn complex business challenges into reliable, repeatable, and efficient AI solutions. You will also contribute to building Evergreen.AI’s reusable frameworks, skills, evaluation tools, and knowledge foundations. This position requires strong engineering fundamentals, practical problem-solving skills, and a growth mindset. You will help ensure our solutions meet enterprise standards for reliability, security, and performance.

AI and Agentic Engineering

• Design and implement agent components including planners, tool interfaces, context managers, and workflow logic.
• Build and optimize retrieval-augmented generation (RAG) pipelines including chunking, embeddings, vector search, ranking, and caching.
• Develop and refine LLM-driven applications using prompting, tuning, and model selection best practices.
• Implement evaluation methods to measure agent quality, correctness, latency, and safety.

Framework and Platform Development

• Contribute to Evergreen.AI’s reusable agent framework, skill libraries, APIs, and microservices.
• Integrate LLMs with enterprise systems using connectors, events, and secure service patterns.
• Build standard approaches for knowledge grounding, memory, and multi-agent coordination.

LLMOps and Production Deployment

• Implement CI/CD pipelines for prompts, embeddings, models, and agent runtime services.
• Build observability dashboards to monitor drift, accuracy, cost, usage, and error patterns.
• Apply resiliency patterns such as retries, fallbacks, circuit breakers, and structured logging.

Collaboration and Delivery

• Partner with product managers, architects, and delivery leads to translate requirements into technical solutions.
• Participate in solution design sessions, technical reviews, and client discussions.
• Contribute to reusable accelerators, templates, best practices, and documentation.

Required

• 5+ years of experience in machine learning, applied AI engineering, or backend software engineering with an AI focus.
• Master’s or Bachelor’s degree in Computer Science or a related field.
• Hands-on experience building and deploying LLM or ML-powered applications in production.
• Proficiency with agentic AI frameworks such as LangChain, Semantic Kernel, or the Assistants API.
• Strong understanding of retrieval systems, embeddings, and vector databases including Pinecone, Milvus, Weaviate, or Chroma.
• Solid Python engineering skills and experience building microservices.
• Experience with Azure or other major cloud platforms, and with containerization and orchestration.
• Familiarity with LLMOps or MLOps practices including CI/CD, model monitoring, and observability.
• Ability to communicate clearly with technical and non-technical partners.

Preferred

• Experience with ontologies, knowledge graphs, or semantic search systems.
• Experience integrating AI systems with enterprise platforms such as Microsoft 365, ServiceNow, or Salesforce.
• Open-source contributions to AI frameworks or libraries.