Generative AI Engineer - LLM & RAG (Hybrid)

Capco; Massachusetts; Hybrid; USD 110,000 - 140,000; Full time

Benefits offered by this job

Medical, Dental, Vision coverage

401(k) with company match

Maternity/Paternity leave

Job summary

Capco is seeking a mid-level Generative AI Engineer to design, develop, and deploy AI-powered solutions built on Large Language Models, RAG, and agent-based architectures. You will collaborate with software engineers, product managers, and AI specialists to deliver scalable, production-grade AI across Capco’s financial services clients.

In this role, you’ll design AI-powered applications, optimize RAG pipelines with vector databases, and create intelligent agents that interact with APIs and

Qualifications

• 2–3 years of professional software/AI engineering experience.
• Hands-on experience with Generative AI tech, LLMs, and leading providers (OpenAI, Anthropic, Gemini, Azure OpenAI).
• Strong Python development with REST APIs, microservices, and scalable backends.

Responsibilities

• Design, build, and deploy AI-powered applications with LLMs and modern Generative AI frameworks.
• Develop and optimize RAG solutions using vector databases and enterprise data sources.
• Create intelligent AI agents/workflows interfacing with APIs and business systems.
• Build scalable REST APIs, backend services, and cloud-native architectures.
• Collaborate with cross-functional teams to translate requirements into production-ready AI solutions.

Skills

Generative AI

LLMs

Python

REST APIs

Microservices

Git

CI/CD

Cloud platforms

RAG architectures

Vector databases

Tools

Pinecone

Weaviate

Chroma

Qdrant

FAISS

Docker

Kubernetes

Job description

Capco is seeking a mid-level Generative AI Engineer to design, develop, and deploy AI-powered solutions built on Large Language Models, RAG, and agent-based architectures. You will collaborate with software engineers, product managers, and AI specialists to deliver scalable, production-grade AI across Capco’s financial services clients.

In this role, you’ll design AI-powered applications, optimize RAG pipelines with vector databases, and create intelligent agents that interact with APIs and