About The Role

Sanas is hiring a Senior Software Engineer to contribute to the technical direction for real-time streaming and inference systems across our product suite (live language translation, noise cancellation, accent translation) and the internal platforms that power them. You will contribute to architecture for low-latency, high-concurrency audio pipelines and lead the design of developer and experimentation platforms that supports model iteration and deployment.

Your Impact:

• Design and build low latency, scalable, and reliable model inference and serving stack for our cutting edge speech models.
• You will mentor and unblock junior engineers, drive cross-team technical decisions, and deliver production systems that operate predictably at scale.

• Work closely with our research team and product engineers to translate cutting edge research into incredible products.
• You'll have significant autonomy to shape our products and directly impact how cutting-edge AI is applied across various devices and applications in speech.

Qualifications

• 4+ years of Software Engineering experience.
• Strong fundamentals with a focus on writing clean & maintainable code.
• Experience building large-scale distributed systems with high demands on model inference, performance, reliability, and observability.
• Strong communication skills with ability to own large scope projects by working cross-functionally across Engineering, AI, Product, Research and Business stakeholders.
• Strong proficiency in Python or Go.
• Experience working with AWS (preferred), GCP or Azure, EKS / Kubernetes.
• Familiarity with batch & real-time streaming protocols like gRPC/protobuf, websockets etc. 
• Familiarity with message queues or similar technologies.
• Deep curiosity about the state of agentic coding tools and how to optimize agent-assisted workflows.
• Nice-to-have: Familiarity with real-time streaming protocols like WebRTC and SIP/SRTP.
• Bachelor’s Degree in Computer Science or related fields.