This is a hybrid role, and the successful candidate will collaborate with internal business partners to deliver AI-enabled solutions with measurable business value. The candidate must have experience working within a team environment as well as independently, on multiple projects simultaneously, and work well within deadlines. The candidate must have experience building production applications on large language models, including prompt and context design, tool calling, retrieval-augmented generation (RAG) over enterprise documents and structured data, and agentic workflows that complete multi-step tasks. Preference will be given to candidates with experience in evaluating non-deterministic systems, chunking and embedding strategies that improve retrieval quality, natural-language-to-data interfaces, integration with enterprise source systems such as ERP or document repositories, and Agile/Scrum delivery. Proficiency in translating user needs into working, supportable systems are imperative and proven / demonstrable experience in this regard is mandatory.
KEY RESPONSIBILITIES:
- Design, build, and deploy AI-enabled applications and agentic workflows that give business users grounded answers from enterprise data.
- Build and tune retrieval-augmented generation solutions, including chunking strategy, embedding generation, and vector search.
- Develop and maintain evaluations that measure answer quality, retrieval relevance, and grounding, and use them to catch regressions.
- Curate source data into retrieval- and agent-ready form, and direct data engineers on the transformations a solution requires.
- Build, containerize, and deploy services and APIs, including versioned releases, orchestration, scheduling, monitoring, and error handling.
- Follow best practices for governance, security, and data protection, including least privilege identity and service account design.
- Collaborate with stakeholders to gather requirements and translate them into technical specifications; communicate advanced concepts clearly to varied audiences.
- Evaluate and recommend models, tools, and platforms to achieve business outcomes, and maintain an up-to-date knowledge of technology trends.
MINIMUM EDUCATION, KNOWLEDGE, SKILLS AND ABILITIES:
- Bachelor’s degree in computer science, Engineering, Data Science, Information Systems or related discipline, or equivalent work experience.
- Three plus years of hands-on experience delivering AI or data solutions, or similar experience in mining, steel making, or related industry.
- Demonstrated skill building applications on large language model APIs, including prompt and context design, tool calling, and cost awareness.
- Demonstrated skill with retrieval-augmented generation patterns, including embeddings, vector search, and grounding against enterprise content.
- Demonstrated skill designing agentic workflows that call tools, maintain state, and complete multi-step tasks, and evaluate them systematically.
- Proficiency in Python and SQL, including cost-aware query design against large datasets.
- Working knowledge of a cloud data platform (e.g., Azure, Databricks, Google Cloud); relevant certification a plus.
- Experience deploying containerized services and APIs and working knowledge of cloud identity and access management and least-privilege design.
- Ability to work independently and manage priorities, with strong organizational and time management skills, excellent communication, and creative problem solving.
Work Environment/Physical Requirements:
- Commuter remote structure.
- Ability to travel 15-20% of the time.
- Must be able to constantly operate a computer.
- Must be able to remain stationary 50% of the time.