AI Application Engineer

We are hiring an AI Engineer to design and operate production-grade AI/ML systems that directly improve product and operational outcomes.

Our current focus is building an AI Agent Platform with a modular architecture:

Gateway → Orchestrator → Agents → Tools → Guardrails → Feedback, enabling automation of complex workflows with strong control, validation and continuous learning.

This role is intentionally broader than AI agents. Depending on priorities, you may also work on:

• Search and retrieval systems (keyword, semantic, hybrid)
• Recommendation, ranking and personalization systems
• AI evaluation, monitoring and reliability systems
• Other AI-powered product or operational systems with measurable business impact

We are not looking for someone who only knows how to prompt models.

We are looking for a strong engineer who can turn ambiguous problems into reliable systems in production.

What You Will Buil

• AI Agent Platform components: orchestration, agent coordination, tool usage, guardrails and feedback loop
• Search and retrieval systems using keyword, semantic or hybrid approached
• Recommendation, ranking and personalization system
• Backend services and APIs that expose AI capabilities safely and reliable
• Monitoring, evaluation and human-in-the-loop workflows for continuous improvement

Responsibilities

• Design and build end-to-end AI/ML systems from problem definition to production rollout and iteration
• Develop and evolve AI Agent workflows, including context handling, tool calling, validation and fallback logic
• Build retrieval, search, ranking and personalization components that connect user intent to the right data or action
• Integrate LLMs with structured and unstructured data via context construction and tool-enabled workflows

Must-have

• Strong software engineering foundation with a production mindset, strong Python skills
• 2-5 years of experience in AI Engineering or ML Engineering
• Experience building backend services and APIs
• Hands-on experience building LLM-based application
• Understanding of: RAG, embeddings, vector database & Retrieval and search pipeline
• Experience in at least one of the following:

+ AI agent or multi-step AI workflow

+ Search, retrieval or relevance system

+ Recommendation, ranking or personalization systems

Nice to have

• Experience with large-scale search or recommendation system
• Experience with agent orchestration frameworks or tool-using LLM system
• Experience with A/B testing, experimentation or evaluation pipeline
• Experience with observability, monitoring and production reliability
• Experience with multimodal systems (voice, OCR, image)
• Experience in high-scale operational domains (fintech, payments, customer operations)
• Experience mentoring or leading projects

How You Work

• You are an engineer first: you care about clean code, maintainability and production reliaility
• You have an AI mindset: you understand when to use rules, ML, LLMs or hybrid approaches
• You have an applied mindset: you start from the problem and choose the simplest effective solution
• You are proactive: you propose, build, test and improve continuously