[Hiring] AI Engineering Lead @ApTask

Role Description

Lead the engineering team building production-grade AI/LLM systems. The lead owns LLM architecture, prompt and evaluation strategy, AI observability, and cost optimization, and mentors engineers to deliver reliable AI capabilities.

Key Responsibilities

• Define and own the architecture of production AI/ML and LLM-based systems, including agentic workflows and RAG patterns.
• Establish prompt engineering standards, prompt versioning and guardrails.
• Build evaluation frameworks (offline and online) to measure accuracy, safety, hallucination and regression.
• Implement AI observability: tracing, token/latency metrics, quality monitoring and drift detection.
• Drive cost optimization across model selection, caching, batching and token usage.
• Lead, mentor and review the work of AI engineers; set coding and quality standards in Python.
• Partner with architecture, security and business teams to ensure responsible-AI and governance controls.
• Absorb the 1-month knowledge transition from the MVP delivery team and own AI technical continuity.

Qualifications

• 10+ years in software engineering, with recent hands-on experience shipping production AI/ML systems.
• Strong expertise in LLM architecture, prompt engineering and evaluation frameworks.
• Advanced Python skills.
• Experience implementing AI observability and cost controls.
• Proven team leadership and technical mentoring experience.

Requirements

• Experience with Langchain/LangGraph, LlamaIndex or similar frameworks; AWS Bedrock / Azure OpenAI.
• Knowledge of AI risk management and model governance in financial services.
• Banking/payments domain exposure.

Education

• Bachelor’s degree in computer science, Engineering, Information Technology, or a related field (or equivalent experience).

Soft Skills

• Clear written and verbal communication with US-based stakeholders.
• Ownership mindset.
• Structured problem-solving.
• Ability to work effectively across onsite–offshore teams.

Screening Must-Haves

• Production LLM systems delivered.
• Evaluation frameworks and AI observability.
• Team leadership.