Senior AI Platform Engineer – Agentic AI

Honeywell•Atlanta, GA

1d•Hybrid

About The Position

Honeywell is seeking a Senior AI Platform Engineer to join its Data Engineering, AI & ML Platform team. The role designs and builds enterprise platform capabilities that let teams create, deploy, evaluate, observe, and operate production-grade AI agents and intelligent applications at scale. It combines software engineering, AI platform engineering, generative AI, agentic systems, data engineering, and MLOps, with an emphasis on reusable services, SDKs, patterns, and components rather than one-off applications. The engineer will develop capabilities for agent reasoning and orchestration, tool integration, enterprise knowledge retrieval, memory and context management, evaluation, observability, and responsible operation. The role collaborates with data and AI/ML engineers, application teams, architects, product teams, and domain experts to turn emerging AI capabilities into secure, reliable, production-grade enterprise services. It is a hands-on individual contributor position suited to an engineer comfortable with ambiguous problems and evolving technologies. The position is based in Atlanta, Georgia, on a hybrid basis. New hires must work onsite Monday through Friday for their first 90 days.

Requirements

At least 8 years of software, data platform, ML platform, or AI engineering experience, including designing, building, and supporting production-grade systems.
Strong Python software engineering expertise, including API and service development, testing, debugging, packaging, design patterns, and modern software development practices.
Experience building cloud-native distributed applications and platforms using containers, Kubernetes, public cloud technologies, CI/CD pipelines, observability, and reliability engineering.
Hands-on experience developing and deploying AI/ML and generative AI solutions, including model serving, lifecycle management, monitoring, operational support, and production deployments.
Experience building LLM and agentic AI applications, including RAG and grounding, enterprise integration and retrieval of structured and unstructured data, orchestration frameworks, and tool/API integration.

Nice To Haves

Experience with LangGraph, LangChain, Semantic Kernel, AutoGen, or equivalent agent orchestration frameworks.
Experience designing multi-agent systems, agent tool ecosystems, planning and reasoning workflows, agent memory, or human-in-the-loop patterns.
Experience with AI evaluation and observability platforms such as LangSmith, MLflow, or equivalent tooling.
Experience with Azure Machine Learning, Azure AI services, Databricks, Kubernetes, or comparable AI/data platforms.
Experience with vector databases, semantic search, knowledge graphs, RDF/SPARQL, Neo4j, ontology engineering, or GraphRAG-style knowledge systems.
Experience building AI systems that integrate with industrial IoT, operational technology, building systems, digital twins, or high-volume telemetry.
Experience building developer platforms, SDKs, internal frameworks, or reusable engineering capabilities used by multiple development teams.
Bachelor's or advanced degree in Computer Science, Engineering, Artificial Intelligence, or a related discipline, or equivalent practical experience.

Responsibilities

Design and build reusable enterprise platform capabilities for developing, deploying, and operating AI agents and multi-agent workflows.
Build frameworks and components that enable agents to securely interact with enterprise APIs, data platforms, applications, tools, and knowledge sources.
Develop agent orchestration patterns without coupling the platform to a single framework.
Build RAG and enterprise knowledge retrieval services, including document ingestion, retrieval pipelines, vector and semantic search, grounding, citations, and contextual enrichment.
Develop systematic evaluation approaches for agents and LLMs, covering task success, response quality, grounding, tool-use correctness, latency, reliability, and cost.
Implement observability and tracing so developers can inspect agent decisions, model and tool calls, failures, performance, and resource consumption.
Design, build, and operate scalable platform services and APIs using Python and FastAPI or comparable production frameworks.
Build reusable APIs, SDKs, libraries, templates, and reference implementations for engineering teams developing and deploying AI applications.
Design cloud-native AI platform services using technologies such as Azure, Kubernetes, Databricks, Azure Machine Learning, MLflow, or equivalent platforms.
Develop production capabilities for model and application deployment, configuration, versioning, experimentation, evaluation, and lifecycle management.
Build automated CI/CD and testing pipelines for AI services, agent workflows, prompts and configurations, and platform components.
Turn prototypes and notebook-based experiments into modular, testable, maintainable, production-quality software.
Design platform patterns that maintain data quality, lineage, access control, and traceability across AI workflows.
Apply production software engineering practices for testing, security, scalability, reliability, and maintainability.
Implement end-to-end observability, tracing, monitoring, and alerting across agent workflows, models, APIs, retrieval systems, and platform services.
Establish mechanisms for handling agent and tool failures, model errors, timeouts, retries, and degraded dependencies.
Implement guardrails, access controls, auditability, and human oversight for enterprise agentic AI workflows.
Optimize AI workloads for latency, throughput, infrastructure utilization, and model and token cost.
Diagnose complex production issues involving AI models, orchestration, data, APIs, infrastructure, and applications.