AI Engineer

The Senior AI Engineer leads the design and delivery of production AI features for PhoenixTeam, translating ambiguous product problems into reliable, well-tested LLM-powered solutions. The role prototypes and ships large language model applications end to end, including retrieval-augmented generation (RAG) pipelines, AI agents, and prompt-driven workflows; evaluates model, embedding, and orchestration options against quality, latency, and cost; builds evaluation and observability pipelines to monitor production AI systems; and partners closely with product, design, and backend engineering to integrate AI services into PhoenixTeam's applications. The engineer also mentors other team members on LLM application patterns and evaluation best practices. This role requires 4+ years of professional software engineering experience with at least 1-2 years building production LLM applications, strong Python skills, excellent written and verbal communication, sound engineering judgment, and the ability to work independently in a fully remote, asynchronous-friendly environment.

Key Functions

• Design, build, and ship LLM-powered features end to end, from prototype to production, including RAG systems, AI agents, and prompt-driven workflows.

• Evaluate and select LLM providers, embedding models, and orchestration frameworks, balancing quality, latency, and cost.

• Build robust prompt engineering and evaluation pipelines, including automated testing and regression checks for model outputs.

• Design and maintain retrieval systems (vector databases, chunking strategies, hybrid search) that ground model outputs in reliable data.

• Partner with product and design to translate ambiguous problems into scoped, testable AI features.

• Instrument AI systems for observability, tracking quality, latency, cost, and failure modes in production.

• Mentor other engineers on LLM application patterns, prompt design, and evaluation best practices.

• Collaborate with backend engineers to integrate AI services into existing application infrastructure via clean, well-documented APIs.

• Stay current with the rapidly evolving LLM and agent ecosystem, bringing new techniques into the team's toolkit.

Minimum Qualifications

• Bachelor's degree in Computer Science, a related field, or equivalent practical experience.

• 4+ years of professional software engineering experience, including 1-2+ years building production applications on top of LLMs (OpenAI, Anthropic, or similar).

• Strong Python skills, with comfort in at least one modern web or backend stack (e.g., Node.js, Django, FastAPI).

• Hands-on experience with RAG architectures, vector databases (e.g., Pinecone, Weaviate, pgvector), and embedding models.

• Practical experience with prompt engineering, structured output generation, and evaluation methodologies for non-deterministic systems.

• Solid understanding of software engineering fundamentals: testing, code review, CI/CD, and production monitoring.

• Excellent verbal and written communication skills, with the ability to work independently in a remote, asynchronous-friendly environment.

Preferred Qualifications or Skills

• Familiarity with agent frameworks and tool-use patterns (e.g., LangChain, LlamaIndex, or custom orchestration).

• Experience fine-tuning or evaluating open-source LLMs.

• Background in traditional ML (classification, ranking, or recommendation systems).

• Experience with cloud infrastructure (AWS, GCP, or Azure) and containerized deployments.

• Prior experience in a startup or fast-moving product environment.

Position Details

• Employment type: Full-Time

• Location: 100% Remote (US-based)

• Hours: 40 hours/week with availability during core business hours

• Start date: ASAP

• Compensation: Competitive salary, equity, and benefits (details provided upon offer)