Senior AI Developer

Senior AI Developer

We are seeking a Senior AI Developer to join our engineering team. In this senior role you will help shape and execute our AI/ML strategy, guiding our journey from early generative-AI capabilities into a mature, production-grade AI practice. You will integrate generative-AI features into our products and internal platforms, combine retrieval-augmented generation (RAG) with knowledge graphs to ground model outputs in our domain data, and own AI features end-to-end — model selection, prompt engineering, retrieval, fine-tuning where appropriate, deployment, observability, cost governance, and compliance posture.

As a senior individual contributor, you will also provide architectural direction and code-level guidance to existing engineering teams who own day-to-day delivery of supporting backend and data-layer work.

Accountabilities and Responsibilities

• Helps set technical direction for AI/ML — evaluates models, frameworks, vector stores, graph databases, evaluation tooling, and orchestration patterns; makes recommendations and leads adoption.
• Designs and implements production generative-AI features using managed foundation-model services, applying guardrails, contextual grounding, structured output, tool use, and agentic workflow patterns.
• Builds retrieval-augmented generation (RAG) pipelines — document ingestion, chunking, embeddings, vector search, hybrid retrieval, and reranking — selecting the storage approach that best fits each use case.
• Designs and operates knowledge graphs to model the domain — schema and ontology design, entity resolution, relationship extraction, and integration with LLM workflows (GraphRAG, hybrid graph + vector retrieval).
• Trains and fine-tunes models where it produces measurable lift, including dataset preparation, supervised and parameter-efficient fine-tuning, baseline evaluation, and deployment.
• Provides architectural direction and code-level guidance to existing .NET and SQL engineering teams responsible for backend services and data-layer integration with AI features.
• Defines and enforces LLMOps / MLOps practices: prompt and model versioning, evaluation harnesses, regression testing, latency and cost SLOs, and reproducible training pipelines.
• Implements observability for AI systems and makes the data actionable across token usage, latency, hallucination and refusal rates, contextual-grounding faithfulness, cost-per-request, and quality metrics.
• Builds and operates AI systems for audit-readiness — data lineage, prompt and model version traceability, decision logging, access controls, and evidence collection.
• Mentors fellow engineers, leads code review, contributes to architecture decision records, and helps shape the team's AI engineering standards.
• Partners with security and compliance to ensure AI systems meet data privacy, PII handling, prompt injection defense, and responsible-AI requirements throughout the model lifecycle.

Position Requirements

• Bachelor's degree in Computer Science, Software Engineering, or a related field, or equivalent professional experience.
• 10+ years of professional software engineering experience.
• 2+ years building production AI/LLM features on a managed foundation-model platform.
• Demonstrable experience training and/or fine-tuning models — supervised fine-tuning, parameter-efficient fine-tuning (LoRA, QLoRA), or classical ML — including dataset preparation, evaluation, and deployment.
• Production experience with knowledge graphs — schema and ontology design, a graph database, and at least one graph query language (Cypher, SPARQL, or Gremlin).
• Demonstrable production experience in regulated environments. Compliance is a hard requirement for this role.
• 3+ years of production cloud experience including at least one managed AI service.
• Solid grounding in prompt engineering, RAG, embeddings, vector search, guardrails, contextual grounding, and LLM evaluation methodology.
• Ability to provide architectural direction and technical guidance to existing engineering teams; senior IC influence rather than line management.
• Strong testing discipline — unit, integration, and contract testing, plus AI-specific evaluation harnesses.
• Excellent written…