LLM & GenAI Engineer — Production RAG Pipelines

Evlo AI; Miami (FL); On-site; USD 120,000 - 180,000; Full time

Job summary

Evlo AI is seeking an ML/Software Engineer to design, build, and ship production-grade LLM systems. You will work on retrieval-augmented-generation pipelines, vector databases, and agent-like workflows, collaborating with researchers, backend engineers, and product leaders.

Ideal candidates have 3–6 years in software/ML engineering, strong Python skills, and hands-on experience with RAG architectures, model fine-tuning, and cloud deployments.

Qualifications

• 3–6 years of software/ML engineering, with at least 2 years shipping LLM-powered systems to production.
• Strong Python engineering skills including async programming, API design, and testing.
• Hands-on production experience with RAG architecture, embedding models, vector DBs, and retrieval quality tuning.
• Experience fine-tuning or evaluating open-source models (Llama, Mistral, Quwen) and using provider APIs (OpenAI, Anthropic, Bedrock).

Responsibilities

• Architect and build RAG pipelines using LangChain, LlamaIndex, or custom retrieval stacks.
• Implement and scale vector database integrations for low-latency semantic search in production.
• Design agentic workflows with tool calling, function execution, and guardrails with LangGraph or custom layers.
• Run fine-tuning workloads (LoRA, QLoRA, DPO) on domain datasets using PyTorch and Hugging Face.
• Build systematic LLM evaluation frameworks with golden datasets and CI integration.
• Deploy and serve models via vLLM, Triton, or managed endpoints, optimizing cost and latency.
• Own observability for GenAI features with tracing and dashboards to surface failures.

Skills

Python

Async programming

API design

Testing

Large codebases

Education

Bachelors degree in CS/Engineering or related field

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

PyTorch

Hugging Face

OpenAI API

AWS

GCP

Azure

LoRA

QLoRA

DPO

LangGraph

Job description

Evlo AI is seeking an ML/Software Engineer to design, build, and ship production-grade LLM systems. You will work on retrieval-augmented-generation pipelines, vector databases, and agent-like workflows, collaborating with researchers, backend engineers, and product leaders.

Ideal candidates have 3–6 years in software/ML engineering, strong Python skills, and hands-on experience with RAG architectures, model fine-tuning, and cloud deployments.