Engineering Manager, Provider Ecosystem

Role overview A hands-on engineering leadership role on the Provider Ecosystem team, which owns the supply side of an AI routing layer used by enterprise customers to access large language models. The position blends people leadership, deep technical work, and external-facing partnership work with model labs and inference providers, reporting to the VP of Engineering. It centres on integrating hundreds of providers and thousands of endpoints and turning benchmark and telemetry data into routing decisions.

Responsibilities - Grow and lead a strong engineering team by hiring, setting the roadmap, staying close to code review and incidents, and advocating for the team with leadership. - Own core provider work, including adapters, the endpoint lifecycle, and routing, serving as the technical counterpart to top providers and running day-zero and stealth launches. - Partner with go-to-market, business development, and legal teams to take new providers from signed NDA to live production in weeks rather than months. - Lead the expansion beyond text into image, video, audio, and embeddings, as well as realtime and batch inference. - Own evaluations and inference quality, and convert that data into routing decisions and direct feedback that helps providers improve.

Requirements - 4+ years of engineering management experience, including building or scaling a team through a period of rapid growth. - Strong technical foundation in distributed systems, API design, and LLM inference, with solid understanding of streaming, tool calling, prompt caching, quantization, and the latency and throughput trade-offs in serving. - Hands-on coding ability and comfort using AI-assisted development tools while leading by example in a team where everyone ships. - Comfort representing technical requirements externally with model labs and partners without a PM in the room. - Data-driven approach to quality, with benchmarks, evals, and production telemetry guiding routing decisions. - Proven ability to recruit and retain strong engineers, high agency, clear communication, and pragmatism about what a lean engineering organization actually needs.

Nice to have - Experience at an inference provider, model lab, or GPU cloud, or building products that consume many LLM APIs at once. - Familiarity with TypeScript, Cloudflare Workers, Postgres, ClickHouse, GCP, or Vercel. - Background in evals, benchmarking, or routing and load-balancing systems. - Experience shipping multimodal APIs or realtime and batch inference, and running vendor security and compliance reviews such as NDA, DPA, and SOC 2.