Python Backend Engineer

Ellipsis Health, Inc.

Oakland, United States of America

1 month ago

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Working hours

Regular working hours

Languages

English

Experience level

Senior

Job location

Remote

Oakland, United States of America

Tech stack

API

Artificial Intelligence

Amazon Web Services (AWS)

Azure

Cloud Computing

Information Engineering

Relational Databases

Python

PostgreSQL

Public Switched Telephone Networks

Queueing Systems

Redis

Twilio

WebSocket

WebRTC

Data Logging

Google Cloud Platform

Large Language Models

Concurrency

Backend

FastAPI

Kubernetes

Information Technology

Low Latency

Kafka

Speech Synthesis

OPUS (Software)

Amazon Web Services (AWS)

gRPC

Microservices

Job description

Design, implement, and maintain Python microservices supporting real-time conversational AI pipelines.
Work on systems including audio capture, streaming transcription, LLM prompt orchestration, speech synthesis, and playback.
Integrate new ASR, TTS, LLM, and memory service providers into the platform.
Build APIs and adapters that allow hot-swapping components without downtime.
Implement streaming transports such as WebRTC, SIP, and telephony endpoints.
Optimize pipelines to achieve ultra-low latency (<500 ms round-trip).
Profile and improve async pipelines using asyncio, FastAPI, and gRPC streaming.
Implement observability using OpenTelemetry, metrics, and structured logging.
Ensure production reliability through retries, circuit breakers, and idempotent messaging.
Maintain HIPAA-compliant security, including encryption, tenant isolation, and secrets rotation.
Collaborate with ML, product, and data engineering teams to develop features like voice cloning, multimodal interactions, and domain memory retrieval.

Requirements

4+ years of experience building production backend systems in Python.
Strong experience with real-time streaming technologies such as WebRTC, WebSockets, or gRPC.
Hands-on experience with async frameworks (asyncio, FastAPI, etc.).
Deep understanding of concurrency, buffering, distributed tracing, and audio codecs (Opus, PCM).
Experience with cloud platforms (AWS / Google Cloud Platform / Azure).
Familiarity with container orchestration (Kubernetes, EKS, GKE).
Experience with message queues (Kafka, SQS, Pub/Sub).
Knowledge of relational databases (PostgreSQL) and in-memory stores (Redis).
Strong communication skills and ability to build observable, production-ready systems., * Degree in Computer Science, Electrical Engineering, or related field.
Experience with voice-agent frameworks.
Hands-on experience with telephony platforms (Twilio, Telnyx), SIP, or PSTN integrations.
Experience integrating multimodal inputs (voice, text, vision) into AI systems.
Exposure to GPU inference or streaming ML pipelines.
Prior experience working in regulated industries (healthcare, finance) and familiarity with SOC 2 / HIPAA compliance.