All roles
Engineering
AI Engineer
Engineering
McKinney, TX
Hybrid
Full-time
As an AI Engineer at Confer, you own production LLM systems that customers depend on: RAG pipelines, agent workflows, and the evaluation harnesses that decide whether a feature ships or rolls back. This is a build role, not a research role.
What you'll do
- Design and implement LLM-powered systems: RAG pipelines, agent architectures, and multi-step reasoning.
- Build evaluation harnesses that measure accuracy, faithfulness, hallucination rate, and latency across model and prompt changes.
- Own retrieval and embedding systems end to end: chunking strategy, vector store management, and hybrid search.
- Deploy and operate AI features in production, including inference cost management and monitoring.
- Partner with product on what genuinely needs a model versus what a simpler approach handles better.
What we're looking for
- 4+ years of software engineering, with at least 2 years on production ML or AI systems.
- Strong Python in a production codebase, not just research notebooks.
- Real LLM application experience: RAG, system-level prompt engineering, evaluation, and at least one shipped foundation-model feature.
- Production experience with a vector database or embedding retrieval system.
- Solid engineering fundamentals: APIs, testing, CI/CD, version control.
Nice to have
- Judgment on when to fine-tune versus improve retrieval or change base models (LoRA, DPO tradeoffs).
- Experience with agentic systems: tool use, multi-agent orchestration, and long-horizon failure modes.
- Classical ML background: knowing when a simpler model beats a costly LLM call.
- Experience shipping AI across more than one product domain.
Apply
Apply for AI Engineer
Tell us a little about you and attach your resume. Fields marked with an asterisk are required.