over 1 year ago
Base Salary
$280k - $350k/yr
Responsibilities
- Own core Inworld Router systems for multi-provider failover, cost- and latency-based routing, live A/B experimentation, and real-time observability at massive scale.
- Build and scale Realtime API, TTS/STT, LLM, Knowledge/RAG, and other API-based model services.
- Develop control, optimization, platformization, developer tooling, billing, and other infrastructure capabilities.
- Collaborate with product managers, engineers, leads, and sibling machine learning teams to determine priorities and deliver products quickly.
- Operate with technical autonomy by selecting appropriate dependencies, standards, and implementation approaches.
- Drive system and engineering improvements while balancing speed and quality.
Requirements
- Excellent programming skills in a statically typed backend language, preferably Go, Python, C++, or Rust.
- Experience developing and deploying cloud-based services handling at least hundreds of queries per second.
- Experience with relational databases such as PostgreSQL or MySQL.
- Hands-on experience with caching systems such as Redis or Memcached, pub/sub or queues, data pipelines such as Flink or Beam, and cloud storage.
- Excellent verbal and written communication skills and the ability to collaborate effectively with product, engineering, and other roles.
- Experience building API gateways, routing or proxy layers, or multi-provider orchestration systems is a bonus.
- Experience with analytics or timeseries databases such as ClickHouse, Timescale, or InfluxDB is a bonus.
- Experience with OpenTelemetry is a bonus.
- Experience with C++ is a bonus.
Benefits
- Equity and benefits in addition to base pay
- Full-time position
- Candidates must be based in the San Francisco Bay Area or willing to relocate
- On-site work in the South Bay office a few days per week
Tech Stack
Categories
About Inworld
Inworld builds real-time voice AI and agent infrastructure for developers, including text-to-speech, speech-to-speech, speech recognition, and LLM routing delivered via APIs and SDKs. Customers use it to create interactive characters and agentic experiences in games, apps, and virtual worlds; revenue comes from usage-based and enterprise licensing. Founded in 2021 and headquartered in Mountain View, California, the company is privately held and works with game studios and large technology firms.