GenAI Engineer: Build Scalable LLMs & Multi-Agent Systems

MoneyLion; New York (NY); On-site; USD 150,000 - 170,000; Full time

Benefits offered by this job

Health benefits

Matched 401k and pension plans

PTO

Parental leave

Gym subsidies

Educational reimbursements

Recognition programs

Job summary

Octus is seeking an AI Engineer focused on CreditAI, owning the full AI stack from design to production reliability. You will architect multi-agent workflows, optimize RAG pipelines, and integrate with cloud LLM services across AWS.

The role demands deep Python, GPU-enabled DL experience, and strong DevOps practices to scale high-throughput data pipelines. You’ll collaborate with product and engineering teams to deliver reliable GenAI solutions, apply RLHF/RLAIF techniques, and continuously

Qualifications

• Bachelor's or Master's degree in Computer Science, Engineering, or related technical field (or equivalent practical experience).
• 5+ years of experience as an AI/ML Engineer or applied AI practitioner.
• Deep Python expertise with production systems at scale; strong software engineering practices.
• Hands-on experience designing and deploying GenAI applications including multi-agent architectures and agentic workflows.
• Experience with GPUs for model training or inference; PyTorch or TensorFlow proficiency.
• Cloud deployments and infrastructure tools (AWS, Docker, GitHub) and DevOps practices.

Responsibilities

• Design and implement multi-agent and agentic orchestration frameworks using agent SDKs and external data sources.
• Build and maintain MCP servers and integrations to extend AI system capabilities.
• Build and optimize RAG pipelines including embedding strategies, vector database, retrieval quality tuning, ingestion design.
• Integrate with managed LLM services across cloud providers to support deployment and cost optimization.
• Fine-tune, optimize, and deploy open-source DL models for production using GPU infrastructure.
• Apply systems thinking to balance quality, scalability, latency, cost, and operational complexity.

Skills

Python

GenAI

LLM architectures

Distributed systems

CI/CD

Problem solving

Communication

Education

Bachelor's or Master's in CS/related field

Tools

AWS

Docker

GitHub

PyTorch

TensorFlow

Vector databases

Embeddings pipelines

Job description

Octus is seeking an AI Engineer focused on CreditAI, owning the full AI stack from design to production reliability. You will architect multi-agent workflows, optimize RAG pipelines, and integrate with cloud LLM services across AWS.

The role demands deep Python, GPU-enabled DL experience, and strong DevOps practices to scale high-throughput data pipelines. You’ll collaborate with product and engineering teams to deliver reliable GenAI solutions, apply RLHF/RLAIF techniques, and continuously