End-to-End AI Engineer: Retrieval, Agents & RAG

DevMations; Pakistan; On-site; PKR 1,800,000 - 3,000,000; Full time

Job summary

DevMations is seeking a hands-on engineer to own AI systems end-to-end in a full-time role based in Pakistan. You will read client corpora, design retrieval strategies, build agent loops, and measure outcomes with real users in mind.

Responsibilities include building retrieval pipelines, orchestrating agents with robust controls, creating eval suites, and reducing latency and per-request costs. You will communicate findings clearly to clients who are not engineers.

Qualifications

• 3+ years building production software, with at least one LLM system shipped to real users.
• Strong Python or TypeScript
• Practical experience with vector search and a retrieval framework
• Comfortable measuring things rather than asserting them

Responsibilities

• Design and build retrieval pipelines — chunking, embedding, hybrid search, re-ranking
• Implement agent orchestration with step limits, retries and human handoff
• Build eval suites and wire them into CI alongside the systems they measure
• Track and reduce per-request cost and p95 latency as first-class metrics
• Write up findings for clients in language a non-engineer can act on

Skills

Production software

Python

TypeScript

Vector search

Job description

DevMations is seeking a hands-on engineer to own AI systems end-to-end in a full-time role based in Pakistan. You will read client corpora, design retrieval strategies, build agent loops, and measure outcomes with real users in mind.

Responsibilities include building retrieval pipelines, orchestrating agents with robust controls, creating eval suites, and reducing latency and per-request costs. You will communicate findings clearly to clients who are not engineers.