Software Engineer - Applied AI / Product Engineering

• →Product & AI Engineering: Design, build, and deploy agent-centric software architectures and end-to-end AI workflows beyond basic conversational interfaces.
• →End-to-End Feature Ownership: Manage the full product development lifecycle—from sitting directly with end-users to understand core pain points, through architectural design, implementation, and deployment.
• →Agent Evaluation & Harnessing: Develop, maintain, and defend robust evaluation frameworks, harness selections, and context management strategies (context window optimization, filtering, and retrieval).
• →Domain Knowledge Extraction: Collaborate directly with industry domain experts to distill complex workflow logic into structured system requirements, prompts, and evaluation metrics.
• →Continuous Paradigm Evaluation: Actively benchmark, test, and re-evaluate emerging LLM models, frameworks, and agent paradigms to continuously refine and improve system performance.

• Proven AI Engineering Experience: Demonstrated track record of shipping production-level software with autonomous LLM agents or workflows at its core.
• Full-Stack / Product Mindset: Ability to own features end-to-end without relying on static product specs or partial hand-offs.
• Technical Rigor & System Design: Ability to defend technical design choices around context management, system evaluation, framework choices, and agent harnesses.
• Strong AI Curiosity: Proactive approach to testing new models, agentic frameworks, and AI tools as they are released.
• Fast Learning & Domain Synthesis: Capability to rapidly absorb complex domain expertise (e.g., financial underwriting or commercial real estate logic) and translate it into technical specifications.
• On-Site Availability: Ability to work full-time on-site, five days a week, at the SoHo, NYC office.

1. Initial Recruiter Screening: Conversation to discuss experience, background, and alignment with the role.
2. Technical Deep-Dive / System Design: Technical discussion focusing on past AI project execution, agent architecture, and system evaluation design choices.
3. On-Site / Product Execution Session: Practical problem-solving and domain synthesis exercise with the core engineering team.
4. Final Leadership Interview: Alignment on team vision, culture, and final offer details.

At MLabs, we are committed to offer equal opportunities to all candidates. We ensure no discrimination, accessible job adverts, and providing information in accessible formats. Our goal is to foster a diverse, inclusive workplace with equal opportunities for all. If you need any reasonable adjustments during any part of the hiring process or you would like to see the job-advert in an accessible format please let us know at the earliest opportunity by emailing human-resources@mlabs.city.

MLabs Ltd collects and processes the personal information you provide such as your contact details, work history, resume, and other relevant data for recruitment purposes only. This information is managed securely in accordance with MLabs Ltd’s Privacy Policy and Information Security Policy, and in compliance with applicable data protection laws. Your data may be shared only with clients and trusted partners where necessary for recruitment purposes. You may request the deletion of your data or withdraw your consent at any time by contacting legal@mlabs.city.