Senior AI Engineer

Role overview Ship AI features into production for client systems where the answers have to be explainable months later. The work blends retrieval engineering, evaluation design, and ownership of how a feature behaves under real-world constraints, often in regulated sectors.

Responsibilities - Build and tune retrieval pipelines over client data, getting indexes and data boundaries right before models enter the picture. - Develop evaluation harnesses that turn a written specification into a measurable score, so completion means something verifiable. - Own AI features end to end, including inference cost, latency budget, failure modes, and rollback strategy. - Join client conversations and explain in plain language what a system will and will not do, including pushing back when warranted. - Review other engineers' work, raise the quality bar, and contribute to shared practices across the team.

Requirements - Senior-level experience designing and shipping production AI systems for external clients or products. - Strong command of retrieval architectures, vector search, and information retrieval trade-offs. - Practical ability to build evaluation and testing infrastructure for LLM-driven features. - Comfort owning data boundaries, access controls, and permissions within AI workflows. - Clear written and verbal communication, including explaining technical decisions to non-technical stakeholders. - Track record of working in client-facing or consulting-style environments.

Nice to have - Background in regulated industries such as healthcare, financial services, or legal technology. - Experience with cost and latency budgeting for inference workloads. - Prior code review or technical mentorship responsibilities.

Benefits and work setup - Permanent, full-time engagement based in Lahore or remote. - Senior-level position with compensation discussed during the first conversation.