AI Engineer (Applied)

BlackStone eIT

- Data classification automation: implementing automated classification to remediate current failures, embedding classification into data pipelines alongside the Governance Lead

- Operational AI agents: building production agents on top of the agentic platform going beyond the sample agents the external partner delivers into real operational workflows

- Agentic platform data contracts: defining what data the platform needs, in what format, with what quality guarantees working with the Principal AI Engineer

- AI service implementation: FastAPI service around LLM APIs with versioned prompt templates

- Classification and briefing prompts: structured prompts returning validated JSON with tags, confidence levels, source attribution

- Prompt versioning: templates in configuration, editable without code changes

- Observability: every LLM call logged with input hash, model version, output, latency, token count

- Fallback logic: graceful degradation when LLM APIs are unavailable

- Quality evaluation: running precision/recall evaluations against human reviewer samples, reporting results, iterating prompts

• 5+ years of experience applying AI and machine learning techniques in a production environment.
• Strong proficiency in programming languages such as Python and familiarity with AI/ML frameworks like TensorFlow, PyTorch, or Scikit-learn.
• Experience with deploying and maintaining AI models at scale.
• Good understanding of data preprocessing, feature engineering, and model evaluation.
• Background in statistics, mathematics, or computer science.
• Ability to collaborate effectively with cross-functional teams and translate business needs into applied AI solutions.
• Excellent problem-solving skills and a practical, solution-oriented mindset.
• Experience with cloud platforms (AWS, GCP, Azure) and MLOps practices is a plus.
• Bachelor s or Master s degree in a relevant field such as Computer Science, Data Science, or AI.
• - LLM APIs (Claude, GPT-4, open-weight models) structured output, JSON mode, system prompts
• - Prompt engineering for classification zero-shot and few-shot
• - Python async API calls, retry logic, exponential backoff
• - LLM evaluation precision/recall, human-AI agreement scoring
• - Structured output JSON schema enforcement, Pydantic validation
• - Open-weight / sovereign model APIs (Falcon, Llama, or equivalent)
• - Token budgeting and context window management
• - AI observability output quality monitoring, anomaly detection
• - FastAPI and Docker