Senior AI Platform Engineer – Agentic AI

Honeywell · Atlanta

We are seeking a Senior AI Platform Engineer – Agentic AI to join our Data Engineering, AI & ML Platform team. This role will help design and build the enterprise platform capabilities that enable teams to create, deploy, evaluate, observe, and operate production-grade AI agents and intelligent applications at scale.

You will work at the intersection of software engineering, AI platform engineering, Generative AI, agentic systems, data engineering, and MLOps. A major focus of the role will be building reusable platform capabilities for agent development, including reasoning and orchestration workflows, tool integration, enterprise knowledge retrieval, memory/context management, evaluation, observability, and responsible operation of AI agents.

Rather than building one-off AI applications, you will help establish reusable services, SDKs, patterns, and platform components that accelerate AI development across Honeywell.

You will collaborate with data engineers, AI/ML engineers, application teams, architects, product teams, and domain experts to take emerging AI capabilities from experimentation to secure, reliable, production-grade enterprise services.

This is a hands-on individual contributor role for an engineer who is comfortable solving ambiguous problems, developing platform capabilities, and turning rapidly evolving AI technologies into maintainable production systems.

The role is based in Atlanta, GA on a hybrid basis. Note: For the first 90 days, new hires must be prepared to work onsite 100% Monday through Friday.

KEY RESPONSIBILITIES
Agentic AI Platform

Design and build reusable enterprise platform capabilities for developing, deploying, and operating AI agents and multi-agent workflows.
Build frameworks and reusable components that allow agents to securely interact with enterprise APIs, data platforms, applications, tools, and knowledge sources.
Develop orchestration patterns using agentic AI frameworks, without coupling the platform to a single framework.
Build services supporting RAG and enterprise knowledge retrieval, including document ingestion, retrieval pipelines, vector/semantic search, grounding, citations, and contextual enrichment.
Develop systematic approaches for agent and LLM evaluation, including task success, response quality, grounding, tool-use correctness, latency, reliability, and cost.
Implement observability and tracing for agent execution so developers can understand agent decisions, model calls, tool calls, failures, performance, and resource consumption.

AI Platform Engineering

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 that make it easier for engineering teams to develop and deploy 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/configurations, and supporting platform components.
Convert prototypes and notebook-based experimentation into modular, testable, maintainable, production-quality software.
Design platform patterns for maintaining data quality, lineage, access control, and traceability across AI workflows.

Production Engineering, Safety & Reliability

Build AI services with production software engineering practices covering 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 failures, tool failures, model errors, timeouts, retries, and degraded dependencies.
Implement appropriate guardrails, access controls, auditability, and human oversight for enterprise agentic AI workflows.
Optimize AI workloads for latency, throughput, infrastructure utilization, and model/token cost.
Diagnose complex production issues spanning AI models, orchestration, data, APIs, infrastructure, and applications.

Honeywell Technologies is a global, pure-play automation company with a legacy of innovating to help solve the world’s most mission-critical challenges, enhancing the quality of life for people and communities around the world. We serve the building, industrial and process sectors with a broad portfolio of services, solutions and products, underpinned by our Honeywell Technologies Accelerator operating system and Honeywell Technologies Forge intelligence layer. By combining the deep domain expertise of our more than 50,000 employees with decades of data from our global installed base, we are uniquely positioned to lead the industrial sector’s transition from automation to autonomy. Design, build, and operate enterprise-scale AI and agentic AI platforms that enable the development, deployment, orchestration, and governance of AI applications and multi-agent systems. Develop reusable platform services, APIs, frameworks, and cloud-native solutions that support LLMs, RAG, enterprise data integration, and knowledge retrieval while ensuring scalability, reliability, security, observability, and cost efficiency. Drive production engineering best practices through CI/CD, testing, monitoring, lifecycle management, and operational support, while implementing guardrails, governance, and performance optimization for mission-critical AI workloads.

More jobs at Honeywell · Infrastructure & IT jobs in Atlanta