Software Engineer, Applied AI

About the role

You will work closely with product, research‑adjacent teammates, and other engineers to ensure AI agents are not only capable but also reliable, steerable, and trustworthy for real‑world tasks. The focus is on turning model improvements into measurable gains in task completion, reliability, and time saved for users.

Key responsibilities

• Design and iterate on agent behavior across GTM workflows, such as sourcing Total Addressable Market lists and handling ambiguous Ideal Customer Profile definitions.
• Map multi‑step manual workflows into agent‑driven flows that match or exceed human performance.
• Build and run evaluation frameworks that verify agents complete tasks correctly, catching regressions and failure modes.
• Develop core agent platform components, including memory systems, tool infrastructure, and retrieval architecture.
• Improve agent performance through prompting strategies, tool‑use design, and context construction, while implementing safety guardrails.

Required profile

• Experience building or shipping production systems with LLMs or AI agents, including multi‑step orchestration, prompting, tool‑use, retrieval, or fine‑tuning.
• Strong backend fundamentals in APIs, databases, and distributed systems.
• Hands‑on experience designing model or agent evaluations and turning qualitative quality questions into measurable signals.
• Systems‑and‑outcomes mindset focused on real user impact rather than isolated model metrics.
• Comfort debugging messy, real‑world failures and a bias toward rapid iteration.

Required skills

• Python
• React
• TypeScript
• AWS (Aurora, Postgres, ECS/Fargate, Lambda, OpenSearch, Clickhouse, Elasticache/Redis)
• Terraform
• Datadog
• Vector search, hybrid search, Retrieval‑Augmented Generation (RAG)
• APIs, databases, distributed systems