Staff)

Sourcedirect Talent•Denver, CO

21h•Hybrid

About The Position

We’re looking for a Software / Applied AI Engineer to build production AI capabilities that make a private AI and data platform scalable, reliable, and repeatable. You’ll own core components of the AI platform, including agentic and multi-agent systems, reusable AI architectures, evaluation and reliability mechanisms, and platform capabilities such as automated fine-tuning and runtime optimization of infrastructure and models. This work operates within clearly defined production boundaries. AI behavior must remain within established limits, and systems are not deployed into production without evaluation, clear ownership, operational controls, and reliable rollback mechanisms. You’ll partner with data and infrastructure teams to translate requirements and feedback into platform capabilities that scale across deployments. This is a hands-on opportunity for someone who thrives in a high-ownership environment and wants to build the infrastructure that enables real-world AI applications.

Requirements

6+ years of experience building and operating production software systems.
Strong fundamentals in distributed systems, performance, and reliability.
Comfortable owning production services end-to-end, including Docker/Kubernetes deployments, REST/gRPC APIs, and disciplined rollout and rollback practices.
Experience building evaluation frameworks, monitoring, and safety or guardrail systems that enable controlled AI behavior in production.
Familiarity with automated evaluation harnesses, drift and quality monitoring, tracing, and structured telemetry.
Strong engineering craft, including clean implementations, thoughtful designs, operational clarity, and thorough documentation.
Experience with technologies such as Python and/or TypeScript/Go, FastAPI-style services, and effective testing practices.
Comfortable working in ambiguous environments and making sound trade-offs involving latency, cost, GPU utilization, and reliability.
Clear communicator and strong collaborator across engineering and commercial teams.
Ownership mindset focused on outcomes rather than tasks.

Nice To Haves

Experience shipping AI-enabled platforms or agentic systems is strongly preferred.
Production experience building agentic and multi-agent systems, orchestration layers, and evaluation frameworks with clear reliability goals.
Experience with tool calling, workflow orchestration, and measurable, repeatable evaluation loops.
Experience designing reusable AI structures, including tool calling, memory and state patterns, policy constraints, and safety or guardrail systems.
Experience deploying these capabilities through stable APIs across multiple applications or environments.
Experience building fine-tuning workflows and runtime optimization systems for private AI deployments.
Familiarity with inference optimization, batching, caching, GPU efficiency, and vLLM-style serving environments.
Experience building monitoring and quality systems for AI behavior that enable measurable improvement and safe rollback.
Familiarity with offline and online evaluation, tracing, structured logs, metrics, and incident-driven iteration.
Strong systems instincts across data, infrastructure, and security constraints that affect AI in production.
Experience with supporting systems such as Kafka-style event systems, Postgres, time-series databases, and secure deployment patterns.

Responsibilities

Build and operate production AI capabilities, including agentic and multi-agent workflows, tool calling, orchestration, and reusable patterns that scale.
Design and implement evaluation, monitoring, and quality systems that make AI behavior measurable, reliable, continuously improving, and safe in production.
Build private AI platform capabilities, including automated fine-tuning workflows, model and runtime optimization, and inference performance improvements under real-world constraints.
Implement safety and operational controls that keep AI behavior bounded and production-ready, including policy constraints, approval workflows, auditability, and rollback mechanisms.
Develop practical interfaces and APIs that make AI capabilities easy to integrate across platform services and customer environments.
Improve developer velocity through automation and tooling, using AI tools to accelerate implementation, testing, documentation, and iteration while applying sound engineering judgment.
Partner with data and infrastructure teams to ensure the right context reaches inference and agent workflows with predictable latency, reliability, and cost.
For Senior-level roles, mentor engineers, review designs, and help raise the technical bar across the organization.