Middle Software Engineer (Generative AI)

We are building reliable, production-grade Generative AI features that power core product experiences.

To deliver these capabilities, we need engineers who can own AI-powered features end-to-end — from design and evaluation through optimization and deployment.

You will work hands-on with LLM APIs and open-source models, prioritizing relevance, stability, latency, and cost efficiency.

This role values deep algorithmic and systems thinking over prompt-only solutions.

WHAT YOU’LL DO

• Design and deliver AI-powered features (search, recommendation, personalization) with

measurable improvements in relevance and user impact

• Build and maintain RAG pipelines using embeddings, reranking, filtering, and other

techniques to ensure predictable and high-quality outputs

• Integrate LLM APIs and open-source models into scalable backend systems running in

production

• Define and track offline and online evaluation metrics to objectively measure and

improve quality

• Optimize the trade-off between quality, latency, and cost to enable sustainable AI usage

at scale

• Implement guardrails, fallback mechanisms, and monitoring to ensure system reliability

and safety

• Conduct code reviews and mentor junior engineers to uphold engineering standards

Must-have

• 2–4 years of professional software engineering experience

• Strong backend engineering fundamentals: APIs, data structures, algorithms, and system design

• Proficiency in at least one backend language (Python strongly preferred; Java, Go, or C# also acceptable)

• Proven ability to debug performance, correctness, and production issues

• Strong reasoning skills for algorithmic and system-level trade-offs

Nice-to-have

• Hands-on experience with AI/ML systems, especially LLMs or generative models

• Prior work on search, ranking, recommendation, or data-intensive systems

• Experience defining and using real-world evaluation metrics (offline and online)