AI Engineer

Better Direct AI is seeking an AI Engineer to build and deliver AI-powered features from early concept through production. The work centers on turning documents and business workflows into reliable tools for sales and engineering teams, with ownership across models, data pipelines, APIs, and user-facing experiences.

Key Responsibilities

• Design document-processing pipelines that convert RFQ PDFs, scanned pages, spreadsheets, and emails into structured outputs such as part numbers, quantities, manufacturers, and shipping addresses.
• Run, optimize, and monitor self-hosted models, including self-hosted LLMs, vision-language models, OCR systems, embedding models, and smaller task-specific models on on-premises NVIDIA GPUs within a Kubernetes-based AI cluster.
• Build search and RAG systems for contracts, product catalogs, and historical quotes using PostgreSQL, pgvector, BM25, vector retrieval, reranking, and deduplication.
• Create tool-using agents that research products across distributor catalogs, including TD SYNNEX, Ingram Micro, and D&H, and prepare quotes for human review.
• Develop classifiers, NER models, sequence-labeling models, and other efficient alternatives when large language models are too slow or costly.
• Produce labeled evaluation datasets, regression tests, and performance benchmarks measuring accuracy, recall, latency, reliability, and cost.
• Implement and maintain Python services using FastAPI, asynchronous processing, Celery, and Redis for extraction, crawling, polling, and other background workloads.
• Integrate AI output into the CRM using Express and Prisma APIs, PostgreSQL schema changes and migrations, and React interfaces.
• Embed AI results into production workflows with confidence scores, human review, feedback capture, permissions, and audit trails.
• Deploy and maintain services using Docker, Git, and documented runbooks. Monitor production jobs, diagnose failures, and support features after release.
• Write clear pull requests, design notes, test plans, and handoff documentation to support ongoing maintenance by other engineers.

Required Qualifications

• U.S. citizenship.
• At least 1 year of experience building application features powered by LLMs or other machine-learning models used in real workflows.
• Strong Python skills, including experience with FastAPI (or a similar framework), asynchronous programming, packaging, and automated testing.
• Working knowledge of TypeScript or JavaScript, and experience building REST APIs or React applications, or the ability to learn these quickly.
• Strong SQL fundamentals and PostgreSQL expertise, including schema design, migrations, indexing, and query optimization.
• Hands-on experience in at least two of the following areas:
  • RAG, embeddings, or semantic search
  • Document extraction or OCR
  • Agent tools, prompting, or workflow orchestration
  • Model fine-tuning or training
  • Model serving with vLLM, SGLang, or a similar platform
  • Creating labeled test sets, selecting appropriate metrics, and objectively measuring performance improvements
  • Working comfort with Linux, Git, and Docker
  • Clear written and verbal communication, including the ability to explain technical trade-offs to non-technical stakeholders

Technologies

• Python, FastAPI
• TypeScript, JavaScript, REST, React
• SQL, PostgreSQL, pgvector, BM25
• PostgreSQL schema changes and migrations
• Express, Prisma
• Docker, Git, Linux, Kubernetes
• NVIDIA GPUs, Celery, Redis
• vLLM, SGLang, OpenAI Codex
• OCR, embeddings, RAG, vector retrieval, reranking, deduplication
• TD SYNNEX, Ingram Micro, D&H
• KServe, Docling, Selenium, Playwright, MinIO, CUDA

Benefits

• 401(k)
• Dental insurance
• Health insurance
• Life insurance
• Paid time off
• Professional development assistance
• Retirement plan
• Vision insurance

AI-Assisted Engineering

AI-assisted development is part of how the team works. Engineers may use tools such as OpenAI Codex to research systems, explore solutions, write code, generate tests, debug problems, and produce documentation. Tool output supports engineering tasks, while the engineer remains responsible for the final result.

• Translate unclear business requests into well-defined technical tasks and acceptance criteria.
• Provide AI tools with appropriate context, constraints, and technical requirements.
• Read, understand, explain, and maintain all code submitted.
• Identify incomplete, unsafe, inaccurate, or unnecessarily complex generated solutions.
• Verify assumptions against the codebase, database, architecture, and application behavior.
• Evaluate trade-offs and choose practical, maintainable solutions.
• Test permissions, security, data integrity, performance, failure modes, and edge cases.
• Use approved tools responsibly when working with company and customer data.
• Troubleshoot and support work after release.

Preferred Qualifications

• Experience running open-weight models such as Qwen, Llama, or Mistral on self-managed GPUs.
• Knowledge of quantization, multi-GPU inference, model optimization, and NVIDIA driver or CUDA troubleshooting.
• Kubernetes experience, particularly with KServe or another model-serving platform.
• Experience with vision-language models or OCR frameworks such as Docling for document understanding.
• Background in traditional NLP techniques such as text classification, named-entity recognition, active learning, weak supervision, or conditional random fields.
• Experience using Celery and Redis, Selenium or Playwright, or S3-compatible storage such as MinIO.
• Familiarity with IT hardware and software products, manufacturer part numbers, and distributor catalogs.
• Contributions to open-source machine learning or developer tooling projects.

What We Value

• Systems thinking: understanding how models, services, databases, interfaces, and integrations work together.
• Data correctness: preventing duplicate, missing, inconsistent, or unauthorized changes.
• Practical problem-solving: identifying root causes and comparing solutions using evidence.
• Production ownership: validating releases, monitoring outcomes, and responding when issues occur.
• Scalability and maintainability: designing for performance, reliability, and extensibility.
• Business understanding: learning why a workflow exists, not only how to implement it.
• Good judgment: knowing when to proceed, investigate further, simplify, or ask for help.
• Continuous learning: acquiring new skills quickly and taking on greater technical ownership over time.

Location and Compensation

• Location: Tempe, AZ (onsite)
• Salary: USD 60,000 - 70,000 per year