AI · Mid-Senior

AI Engineer (RAG & Agents)

Design retrieval pipelines and agentic workflows that survive real production traffic.

Remote · GlobalFull-timeAI$55k - $90k

Browse other roles

Tools you'll live in

PythonLangChainLlamaIndexPostgres/pgvectorFastAPIAWS

Interview loop

Intro call

Background, motivation, comp alignment.

Paid exercise

A small, realistic task tied to the role.

Deep dive

Portfolio/code walkthrough and how you think.

Team fit

Meet two teammates and a delivery lead.

About the role

You will design and ship retrieval-augmented and agentic systems for client products — from data ingestion and chunking strategy to evaluation harnesses that keep hallucination rates low in production.

What you'll do

Design RAG pipelines: chunking, embeddings, retrieval, reranking

Build and orchestrate multi-step agent workflows with tool use

Set up evaluation and observability for LLM-backed features

Optimize latency and cost across model and infra choices

Partner with product to scope what agents should and should not do

What we're looking for

2+ years shipping LLM-backed features to production

Strong Python and API design fundamentals

Hands-on experience with vector databases and embeddings

Comfort reasoning about prompt/context engineering trade-offs

Clear written communication in an async team

Bonus Points

Fine-tuning experienceExperience with eval frameworksOpen-source LLM tooling contributions

Benefits

Remote-first

Work from anywhere with 4 hours of overlap with Karachi time.

Flexible hours

Own your calendar. Deep-work blocks are protected.

$1,200 learning budget

Courses, conferences, books, certifications — yearly.

Top-tier hardware

M-series laptop, monitor, and desk stipend on day one.

Health cover

Medical coverage for you and your immediate family.

Apply in 5 minutes

Send your CV, portfolio, or GitHub. No cover letter needed — just tell us what you shipped.