Senior Backend Engineer, Infrastructure

Ellipsis Health; San Francisco (CA); On-site; USD 175,000 - 250,000; Full time

Benefits offered by this job

401k matching

Health, vision, and dental insurance

Flexible paid time off

Job summary

Ellipsis Health is a health-tech company building AI-powered voice systems to improve staffing and reduce admin burdens. The team develops real-time voice pipelines, scalable back-end services, and privacy-conscious cloud architectures.

We are hiring a senior backend engineer to design, implement, and maintain Python micro-services for conversational AI orchestration, streaming, and low-latency delivery in production with HIPAA considerations.

Qualifications

• 4+ years building production back-ends in Python.
• Experience with real-time streaming systems (WebRTC/WebSockets/gRPC).
• Proficiency with asyncio, FastAPI, or similar async frameworks.
• Strong cloud and container orchestration knowledge (AWS/GCP/Azure, Kubernetes).
• Relational and in-memory stores modeling for conversational state.

Responsibilities

• Expand and maintain real-time voice pipeline: design, implement, and maintain Python micro-services for conversational AI orchestration.
• Integrate new providers & transports; wire up endpoints and adapters for hot-swapping components.
• Deliver ultra-low latency: profile async pipelines, optimize buffering and back-pressure.
• Instrument and observe: emit traces, metrics, and logs; define SLOs for latency and reliability.
• Harden for production: implement retries, idempotency, circuit breakers, and HIPAA security.
• Collaborate with ML, product, data engineering, and client-SDK teams on voice cloning and memory retrieval.

Skills

Python

Real-time streaming

Async frameworks

Cloud platforms

Kubernetes

Datastore: PostgreSQL

Redis

Distributed tracing

Effective communication

Education

BS/MS in CS or related field

Tools

WebRTC

WebSockets

gRPC

Job description

Ellipsis Health is developing cutting-edge AI/ML products to address healthcare staffing issues and administrative burdens. The platform employs conversational AI and patented vocal biomarker technology to deliver improved healthcare experiences for clients and patients. The team is headquartered in Silicon Valley and is funded and supported by preeminent venture capital groups and healthcare institutions.

Responsibilities

• Expand and maintain our real-time voice pipeline: design, implement, and maintain Python micro-services for conversational AI orchestration—audio capture, streaming transcription, prompt/LLM logic, synthesis, and playback.
• Integrate new providers & transports: add plug-ins for emerging ASR, TTS, LLM, and memory services; wire up WebRTC, SIP, or phone endpoints; build adapters that allow hot-swapping components without downtime. Build API endpoints.
• Deliver ultra-low latency (<500 ms round-trip): profile async pipelines (asyncio, FastAPI, gRPC), optimize buffering, concurrency, and back‑pressure handling.
• Instrument & observe every hop: emit structured traces (OpenTelemetry), metrics, and logs for each pipeline stage; define SLOs for first-token latency, end‑to‑end latency, and streaming reliability.
• Harden for production: implement graceful retries, idempotent message passing, circuit breakers, and HIPAA‑compliant security (encryption in transit, per-tenant isolation, secrets rotation).
• Collaborate cross‑functionally with ML, product, data engineering, and client‑SDK teams to deliver features such as voice cloning, multimodal hand‑offs, and domain‑specific memory retrieval.

Qualifications

• 4+ years building production back‑ends in modern Python.
• Proven experience with real‑time streaming systems—WebRTC, WebSockets, or gRPC streaming—and proficiency with asyncio, FastAPI, or similar async frameworks.
• Deep understanding of concurrency, buffering, audio codecs (Opus, PCM), and distributed tracing.
• Solid understanding of AWS/GCP/Azure, including container orchestration (Kubernetes/EKS/GKE), message queues (Kafka/SQS/Pub/Sub), and IaC (Terraform).
• Solid grasp of relational (PostgreSQL) and in‑memory (Redis) data stores; able to model and persist conversational state.
• Excellent communication skills and a bias for measured, observable, and continuously deployable software.

Bonus Points

• B.S./M.S. in CS, EE, or related fields.
• Familiarity with voice‑agent frameworks.
• Hands‑on with telephony (Twilio, Telnyx), SIP, or PSTN integrations.
• Experience integrating multimodal inputs (vision, text chat) into voice agents.
• Familiarity with GPU inference and streaming pipelines.
• Prior work in regulated industries (healthcare, finance) and comfort preparing for SOC 2 / HIPAA audits.

Salary and Benefits

We offer competitive salary and benefits, including 401k matching up to a certain percentage of your salary, health, vision, and dental insurance, and very flexible paid time off.

The typical salary range for this role is $175,000 to $250,000 USD. The amount offered will be determined by a variety of factors including but not necessarily limited to your individual skills, qualifications, and past experience relative to the requirements of the role.

Background Checks

As a health technology company, we reserve the right to run a background check on any applicant to which we extend an offer and to re‑perform any such check at any time during the course of employment. Please know that there is no set policy on rejecting candidates because of certain background check results, and that we look at a candidate as a whole before making any decisions. We comply with all “ban the box” laws in applicable jurisdictions.

Assistance

If you have a disability or otherwise require any assistance whatsoever in the application or recruitment process, please feel free to submit a request to [e-mail].