AI Engineer

Triumphs of Talent; McLean (VA); On-site; USD 180,000 - 240,000; Full time

Job summary

Triumphs of Talent is seeking a Senior AI/LLM Engineer to deliver production AI features for a product-driven company. You will design and implement end-to-end AI systems, including RAG pipelines and embeddings, and work with major providers like OpenAI and Bedrock.

The role requires hands-on experience with LLMs in production, strong Python/Node.js skills, and a track record building recommendation/review systems. You will collaborate with product and engineering teams.

Qualifications

• 10+ years of ML/AI engineering experience.
• 3+ years hands-on LLM/GenAI in production.
• Strong Python and Node.js skills.
• Experience building product-based AI/ML solutions.
• Hands-on experience with recommendation/review systems.
• Strong RAG, embeddings, vector databases, and retrieval experience.
• Experience with LLM APIs and orchestration frameworks.
• Strong AWS Cloud experience, preferably Bedrock.
• GenAI evaluation and monitoring experience.
• Ability to explain LLM usage and production implementation.

Responsibilities

• Design and build AI/LLM-powered product features from development through production.
• Develop recommendation and review-based systems using ML/GenAI.
• Build and optimize RAG pipelines, including embeddings, vector databases, chunking, retrieval, and re-ranking.
• Integrate and work hands-on with LLMs such as OpenAI, Anthropic, Gemini, Llama, or similar.
• Build scalable data ingestion and AI pipelines.
• Deploy, monitor, and optimize AI solutions using AWS Cloud.
• Implement AI evaluation, observability, and production monitoring.
• Work with engineering/product teams to deliver scalable AI features.

Skills

ML/AI Engineering

LLM/GenAI in production

Python

Node.js

Product-based AI/ML

Recommendation systems

RAG & embeddings

Vector databases

LLM APIs/orchestration

AWS Cloud (Bedrock)

GenAI evaluation & monitoring

Production LLM explanation

Tools

OpenAI API

AWS Bedrock

GenAI APIs

Job description

We are looking for a Senior AI/LLM Engineer with strong experience building production AI solutions for product-based companies. The ideal candidate will have hands‑on experience with recommendation/review systems, LLMs, RAG, and AWS Cloud.

Key Responsibilities

• Design and build AI/LLM-powered product features from development through production.
• Develop recommendation and review-based systems using ML/GenAI.
• Build and optimize RAG pipelines, including embeddings, vector databases, chunking, retrieval, and re‑ranking.
• Integrate and work hands‑on with LLMs such as OpenAI, Anthropic, Gemini, Llama, or similar.
• Build scalable data ingestion and AI pipelines.
• Deploy, monitor, and optimize AI solutions using AWS Cloud.
• Implement AI evaluation, observability, and production monitoring.
• Work with engineering/product teams to deliver scalable AI features.

Mandatory Skills

• 10+ years of ML/AI Engineering experience.
• 3+ years of hands‑on LLM/GenAI experience in production.
• Strong Python and Node.js skills.
• Experience building product-based AI/ML solutions.
• Hands‑on experience with recommendation/review systems.
• Strong RAG, embeddings, vector databases, and retrieval experience.
• Experience with LLM APIs and orchestration frameworks.
• Strong AWS Cloud experience, preferably Amazon Bedrock.
• Experience with GenAI evaluation and monitoring.
• Ability to clearly explain which LLMs they have used and how they were implemented in production.