This is a remote position.
We are looking for a highly capable Tech Lead to design and deliver an AI-enabled product from scratch in an environment where requirements may initially be unclear or incomplete. This role requires someone who combines strong software engineering fundamentals, product thinking, and hands-on experience building systems powered by LLMs or other AI technologies. The ideal candidate is comfortable operating in a small company environment, working directly with stakeholders to transform ambiguous business needs into scalable technical solutions. This is a highly hands-on role requiring strong autonomy, pragmatic decision-making, and the ability to structure messy problem spaces.
Job Activities
- Design and implement scalable architectures for AI-enabled products, including LLM integrations, structured workflows (e.g., classification, extraction, reasoning), and RAG or embedding-based solutions.
- Define technical direction and make pragmatic technology decisions, balancing speed, quality, cost, and reliability, while ensuring maintainability and strong engineering standards.
- Evaluate and improve AI system performance through structured feedback loops, guardrails, and fallback strategies.
- Collaborate closely with stakeholders to translate ambiguous business needs into clear technical solutions, influencing product roadmap and prioritization.
- Own delivery by breaking down complex initiatives, coordinating team efforts, and ensuring timely execution of key milestones.
- Lead by example through hands-on development, code reviews, and mentorship, fostering a high-quality and scalable engineering culture.
- Continuously improve processes, documentation, and development workflows to support team efficiency and growth.
Requirements
- Strong experience as a Tech Lead or Senior Engineer, with the ability to design scalable systems from scratch across modern web architectures (frontend and backend).
- Solid expertise in API design, database modeling, software architecture patterns, and scalability fundamentals.
- Hands-on experience integrating LLM APIs into production systems, with a strong understanding of prompting strategies, structured AI workflows, and concepts such as RAG, embeddings, semantic search, and tool/function calling.
- Ability to evaluate and optimize trade-offs between model performance, cost, and latency, while ensuring reliability through guardrails and structured output strategies.
- Strong product and problem-solving mindset, with the ability to identify gaps, structure ambiguous problems, and make decisions with incomplete information.
- Excellent communication skills, able to simplify complex technical concepts and effectively align with non-technical stakeholders, including negotiating scope and priorities.
Nice to Have