Job Description
Title: Senior AI Engineer
Location: Remote
Duration: 12+ months
Job Summary
We are seeking a Senior AI Engineer to design, develop, deploy, and support enterprise-grade Generative AI and Large Language Model (LLM) applications in a regulated financial services environment. The ideal candidate will have strong hands-on experience with agentic AI, LLM orchestration, Retrieval-Augmented Generation (RAG), Python, AI evaluation, cloud services, and production deployment. This role requires the ability to take AI solutions from initial design through production launch and provide ongoing operational support.
Key Responsibilities
- Design, develop, and deploy enterprise-grade LLM and Generative AI applications.
- Build agentic AI workflows using frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, or Amazon Bedrock Agents.
- Develop and optimize RAG pipelines, including embeddings, indexing, vector retrieval, and retrieval quality.
- Build scalable backend services and APIs using Python 3.11+, FastAPI, and asynchronous programming.
- Implement LLM evaluation strategies using golden datasets, evaluation metrics, LLM-as-judge, and automated testing frameworks.
- Monitor and support production AI applications, including incident response, regression management, and performance optimization.
- Implement AI observability through tracing, structured logging, and quality, latency, and cost monitoring.
- Integrate AI applications with REST APIs, enterprise data pipelines, and event-driven services.
- Ensure enterprise security, access control, data protection, compliance, and auditability.
- Collaborate with engineering, business, security, and compliance teams to deliver reliable AI solutions.
Qualifications
- Hands-on experience developing LLM/Generative AI applications.
- Proven experience deploying at least one enterprise-grade AI application into production and supporting it after launch.
- Strong Python 3.11+ skills, including type annotations, automated testing, asynchronous programming, and API development.
- Hands-on experience with LLM orchestration or agentic AI frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, or Amazon Bedrock Agents.
- Strong understanding of RAG, embeddings, vector databases/retrieval, indexing strategies, and retrieval optimization.
- Experience with LLM evaluation, golden datasets, evaluation metrics, and non-deterministic output testing.
- Experience with cloud services, REST APIs, data pipelines, and event-driven architectures.
- Knowledge of AI observability, production monitoring, security, and enterprise compliance requirements.
Asked to add a skill to your resume in a hurry? Pick the resume, type the skill, and Add a Skill gives you the lines to add. Add a skill →
View Similar Jobs
Similar jobs which you may be interested in. Typically using your existing skillset.