Senior AI/ML Engineer: Production-grade Gen AI & RAG

Triunity Software, Inc.; Ocala (FL); Sur place; USD 140 000 - 190 000; Plein temps

Avantages offerts par ce poste

Bonus based on performance

Health insurance

Training & development

Résumé du poste

Triunity Software, Inc. is seeking a talented AI/ML Engineer to join our growing team in the United States. You will work on cutting-edge AI/ML solutions, including retrieval-augmented generation, embeddings, and LLM orchestration, to deliver scalable cloud-based services and REST APIs.

The role emphasizes performance, observability, and governance in regulated environments. Required are strong Python (3.11+), asynchronous programming, and testing skills, plus experience with LLM frameworks and

Qualifications

• 5+ years of overall software engineering experience.
• 2+ years of hands-on LLM/Generative AI development experience.
• Demonstrated experience deploying at least one enterprise-grade AI/LLM application into production.
• Experience owning and supporting live AI applications, including incident management and root-cause analysis.
• Exposure to enterprise security and compliance reviews.

Connaissances

Python

Asynchronous programming

Type hints

Automated testing

LLM development

RAG

Embeddings

Indexing

Retrieval optimization

LLM orchestration

LLM evaluation

Golden datasets

Evaluation metrics

LLM-as-judge

REST APIs

Data pipelines

Event-driven architecture

Observability

Security/compliance

Outils

FastAPI

PostgreSQL

Aurora PostgreSQL

Vector extensions

AgentCore

Agentic AI

Kubernetes

Helm

Terraform

CI/CD

Apache Kafka

Datadog

OpenTelemetry

Document AI

OCR

Description du poste

Triunity Software, Inc. is seeking a talented AI/ML Engineer to join our growing team in the United States. You will work on cutting-edge AI/ML solutions, including retrieval-augmented generation, embeddings, and LLM orchestration, to deliver scalable cloud-based services and REST APIs.

The role emphasizes performance, observability, and governance in regulated environments. Required are strong Python (3.11+), asynchronous programming, and testing skills, plus experience with LLM frameworks and