Production GenAI & LLM Engineer: RAG, Tuning & Pipelines

Evlo AI; Washington (District of Columbia); On-site; USD 180,000 - 260,000; Full time

Job summary

Evlo AI is seeking a senior AI engineer to build production-grade LLM and generative AI systems, focusing on RAG pipelines, agentic workflows, and fine-tuning infrastructure. You will work on retrieval architectures, model optimization, and serving infrastructure with emphasis on latency, cost, and reliability.

This is hands-on engineering with impact across prototype to production. You will join a small, senior team that influences architecture decisions and ships features powering

Qualifications

• 3–8 years in software or ML engineering.
• At least 2 years of production experience with LLMs.
• Bachelor's degree in Computer Science, Engineering, or equivalent.

Responsibilities

• Design and ship production RAG systems with retrieval, chunking, and hybrid search.
• Build and tune vector database integrations and embedding pipelines.
• Develop agentic workflows and tool-use pipelines with error handling and guardrails.
• Implement systematic LLM evaluation, benchmarks, and regression testing.
• Run parameter-efficient fine-tuning and instruction tuning on domain datasets.
• Optimize inference cost and latency via quantization and batching.

Skills

Python

Async programming

API design

Cloud infra

RAG architectures

Vector databases

Embedding models

PEFT fine-tuning

LLM observability

Education

Bachelor's degree in Computer Science, Engineering, or equivalent

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

pgvector

Kubernetes

PyTorch

Triton

Job description

Evlo AI is seeking a senior AI engineer to build production-grade LLM and generative AI systems, focusing on RAG pipelines, agentic workflows, and fine-tuning infrastructure. You will work on retrieval architectures, model optimization, and serving infrastructure with emphasis on latency, cost, and reliability.

This is hands-on engineering with impact across prototype to production. You will join a small, senior team that influences architecture decisions and ships features powering