Senior AI Engineer

Quick Facts

Senior hands-on role building production AI systems, including LLM applications, agents, and RAG pipelines.

Description

You will own AI applications and reusable services end-to-end—from problem framing with domain experts through prototyping, production deployment, monitoring, and ongoing support. The work includes building agents and multimodal applications, designing LLM workflows (including tool calling and structured outputs), and developing grounded RAG pipelines that ingest and parse engineering and business data. You will also deploy and operate Python services on Azure, integrate AI with engineering/manufacturing and business tools via APIs, and continuously improve accuracy, reliability, latency, and cost.

Responsibilities

• Own AI applications and reusable services end-to-end: prototyping, integration, production deployment, monitoring, and support.
• Build agents, multimodal applications, LLM workflows, and RAG pipelines using prompt design, tool calling, structured outputs, embeddings, and hybrid search.
• Ingest and parse messy inputs (datasheets, schematics, test logs, media, business data) into grounded AI capabilities.
• Integrate AI with engineering tools, manufacturing/test systems, and business applications via APIs and MCP servers, with validation, security, and human oversight.
• Apply classical ML where appropriate (classification, anomaly detection, computer vision, audio processing) and deploy/monitor alongside LLM systems.
• Create repeatable evaluations to improve accuracy, reliability, latency, and cost.
• Develop and operate Python services on Azure with PostgreSQL, Terraform, containers, CI/CD, and observability.
• Propose architectures, reusable patterns, and evaluate new models/tools in collaboration with the engineering manager.
• Collaborate with stakeholders to clarify requirements and priorities; mentor engineers through code/design reviews.

Requirements

• 5+ years of software engineering experience; must include delivering and supporting production LLM applications beyond proof-of-concept.
• Strong Python and backend skills (API design, testing, debugging, maintainable software).
• Hands-on experience with LLM APIs, prompt design, and tool-enabled agents using LangChain, LangGraph, or equivalents.
• Practical RAG experience: embeddings, vector and hybrid search, reranking, and measuring retrieval/answer quality.
• Solid ML fundamentals: data processing, feature engineering, model training and evaluation; ability to ship non-LLM models to production using PyTorch, scikit-learn, NumPy, and pandas.
• Cloud deployment experience, preferably Azure, including containers, CI/CD, infrastructure as code, and monitoring.
• Strong SQL skills, preferably PostgreSQL; understanding of authentication, access control, and secure data handling.
• Ability to communicate technical trade-offs to technical and non-technical audiences; independence and mentoring capability.
• Bachelor’s or Master’s in Computer Science, Engineering, or related field, or equivalent experience.

Benefits

The posting emphasizes a hands-on ownership model for production AI systems, end-to-end responsibility, and opportunities to influence technical direction with mentorship and architecture work.