Job Summary
The AI Engineer (Python + LLM) is a senior-level engineering role focused on building, enhancing, and supporting production-grade AI applications and agentic systems. The role involves developing agentic protocols that interoperate across customer platforms to validate, transform, ingest, and structure data, convert unstructured data into standardized formats, and transfer processed information to agents on other platforms. The engineer will design reliable, secure, and measurable AI solutions for business workflows, analysis, and decision-making while collaborating with subject matter experts (SMEs) and business stakeholders to incorporate domain knowledge. The role also includes building reusable foundations for AI development, evaluation, deployment, and operations, with longer-term opportunities to adapt and fine-tune existing large language models (LLMs) for domain-specific applications.
Key Responsibilities
• Enhance, maintain, and support existing AI applications and agentic systems in production environments.
• Design and develop new AI capabilities to support business workflows, analysis, and decision-making.
• Build and maintain reusable foundations for AI development, evaluation, deployment, and operations.
• Develop agentic protocols that validate, transform, ingest, and structure data, convert unstructured data into standardized formats, and exchange processed information with agents on other platforms.
• Collaborate with business stakeholders and SMEs to understand complex business domains and incorporate domain knowledge into AI systems.
• Select appropriate LLMs based on reasoning capabilities, latency, cost, context requirements, and tool-use capabilities.
• Implement retrieval-augmented generation (RAG), tool calling, structured outputs, and agent orchestration.
• Apply model fine-tuning and post-training techniques when they provide better outcomes than prompting or retrieval-based approaches.
• Develop and maintain AI evaluation processes at scale, including prompt and agent instruction versioning.
• Implement monitoring and observability across the AI lifecycle to support reliability, performance, and continuous improvement.
• Apply production-grade engineering practices across the software development lifecycle, including building, testing, and deploying AI solutions.
• Explore opportunities to adapt and fine-tune existing LLMs for custom, domain-specific agent applications as business needs evolve.
Required Qualifications
• Strong Python programming skills and experience with production-grade software engineering.
• Experience building, testing, and deploying reliable applications in production environments.
• Hands-on experience developing and operating LLM applications in production, beyond prototypes or proof-of-concept solutions.
• Understanding of LLM selection and trade-offs involving reasoning capabilities, latency, cost, context length, and tool use.
• Background in machine learning and experience with LLM fine-tuning techniques, including Supervised Fine-Tuning (SFT) and Parameter-Efficient Fine-Tuning (PEFT).
• Familiarity with Direct Preference Optimization (DPO), Reinforcement Learning from Human Feedback (RLHF), or Reinforcement Fine-Tuning (RFT) is an advantage.
• Experience with retrieval-augmented generation (RAG), tool calling, structured outputs, and agent orchestration.
• Experience implementing AI evaluation processes at scale.
• Ability to manage prompt and agent instruction versioning.
• Experience with monitoring and observability across the AI lifecycle.
• Ability to learn complex business domains and collaborate effectively with SMEs and stakeholders.
• Pragmatic, outcome-focused engineering approach, with an emphasis on building reliable, secure, and measurable systems.
Preferred Qualifications
• Knowledge of data engineering concepts and practices.
