Core Engineer - Software / Applied AI

Sourcedirect Talent•Denver, CO

2d•Hybrid

About The Position

Our client is seeking a Core Engineer focused on Software / Applied AI to build production-grade AI capabilities that make a next-generation edge platform scalable, reliable, and repeatable. In this role, you will own critical components of a private AI platform, including agentic and multi-agent systems, repeatable AI architectures, evaluation and reliability frameworks, and platform capabilities such as automated fine-tuning and runtime optimization. This work operates within clearly defined industrial production boundaries — AI behavior must be measurable, controlled, and fully reversible before reaching production. You will partner closely with data and infrastructure teams to translate real-world requirements into scalable platform capabilities. This is a hands-on, high-ownership role ideal for engineers who want to build the infrastructure that makes real-world AI deployments safe and dependable.

Requirements

6+ years building and operating production software systems
Experience shipping AI-enabled platforms or agentic systems strongly preferred
Strong distributed systems, performance, and reliability fundamentals
Experience owning production services end-to-end (e.g., Docker/Kubernetes, REST/gRPC APIs, controlled rollouts)
Experience building evaluation frameworks, monitoring, and AI safety/guardrail systems
Strong engineering craft with clean, well-documented implementations
Proficiency in Python and/or TypeScript/Go and modern service frameworks (e.g., FastAPI-style)
Comfortable navigating ambiguity and real-world constraints (latency, cost, GPU utilization, reliability)
Clear communicator and strong cross-functional collaborator
Ownership mindset focused on outcomes

Nice To Haves

Production experience with agentic or multi-agent systems and orchestration layers
Experience designing reusable AI patterns (tool calling, memory/state, policy constraints, guardrails)
Experience building fine-tuning pipelines and runtime optimization for private AI deployments
Background in AI monitoring and quality systems enabling safe rollback and continuous improvement
Strong systems intuition across data, infrastructure, and security constraints
Familiarity with event/data systems (e.g., Kafka), operational stores (e.g., Postgres or time-series DBs), and secure deployment patterns

Responsibilities

Build and operate production AI capabilities including: Agentic and multi-agent workflows, Tool calling and orchestration, Repeatable AI patterns that scale
Design and implement evaluation, monitoring, and quality systems to ensure AI reliability and continuous improvement
Develop platform capabilities for private AI, including: Automated fine-tuning workflows, Model and runtime optimization, Inference performance improvements under real-world constraints
Implement safety and operational controls such as: Policy constraints, Approval workflows, Auditability, Rollback mechanisms
Build pragmatic APIs and interfaces to integrate AI capabilities across platform services
Improve developer velocity through automation and AI-assisted tooling
Partner with data and infrastructure teams to ensure high-quality context reaches inference and agent workflows
For senior levels: mentor engineers, review designs, and raise the technical bar