Role Purpose
We are seeking an experienced AI/ML Engineer to design, evaluate, and productionize agentic AI systems that autonomously or semi-autonomously plan tasks, invoke internal and external tools, reason over structured and unstructured data, and deliver measurable business outcomes. This role emphasizes reliability, safety, scalability, and auditability in enterprise environments.
Key Responsibilities
Agentic AI & LLM Engineering
- Architect and build tool-using AI agents, including function/tool calling, routing, planning, reflection/self-critique, and memory/state management.
- Design and implement multi-agent workflows (e.g., specialist, reviewer, executor patterns) using LangGraph, AutoGen, CrewAI, or equivalent frameworks.
- Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, including indexing, chunking strategies, hybrid search, reranking, and citation-first outputs.
- Implement guardrails and safety controls, including prompt and policy templates, PII detection/redaction, allow/deny tool lists, and controlled execution.
- Enforce structured outputs using JSON schemas, Pydantic models, or equivalent validation frameworks.
Data Science & Machine Learning
- Develop, train, and deploy classical and modern ML models, including classification, regression, time series forecasting, anomaly detection, and NLP.
- Perform feature engineering, model selection, error analysis, and performance optimization.
- Combine symbolic rules and learned models to improve reliability, explainability, and robustness.
- Design and execute offline and online experiments, including baseline comparisons, ablation studies, and causality/sensitivity analyses where applicable.
Required Qualifications
- Strong experience in Python and ML/AI engineering in production environments.
- Hands-on experience with LLMs, agentic architectures, and tool-calling frameworks.
- Proven expertise in RAG architectures and vector search techniques.
- Solid foundation in machine learning, statistics, and data science workflows.
- Experience implementing AI safety, governance, and validation controls.
Preferred / Nice-to-Have Skills
- Experience with LangGraph, AutoGen, CrewAI, or similar agent orchestration frameworks.
- Familiarity with vector databases (Pinecone, FAISS, Weaviate, OpenSearch, etc.).
- Exposure to cloud platforms (AWS, Azure, GCP) and MLOps practices.
- Knowledge of enterprise data privacy, compliance, and audit requirements.
- Experience deploying AI systems in regulated or large-scale enterprise environments.
Equal Opportunity Employer
We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.