Video Engineer

Role overview

The client is building a multimodal AI platform that processes multi-hour video, audio and text to generate structured insights, narratives and highlight workflows for broadcasters and media organisations.

We are seeking a Backend / Platform Engineer to design and build high-throughput media pipelines, robust APIs, and model-serving infrastructure that connect our AI engine (video perception + multimodal reasoning) to real products and customer environments.

This is not a CRUD‑only backend role.

You will work on:

• long‑running jobs
• distributed processing
• GPU inference orchestration
• storage for embeddings and metadata
• integration with AI models
• reliability and observability at scale

Key responsibilities

Media ingestion & processing pipelines

• Design and implement ingestion pipelines for multi‑hour video and audio content.
• Build microservices for frame extraction, audio processing, transcription integration and metadata generation.
• Handle long‑running, asynchronous jobs using queues, workers and robust retry strategies.
• Integrate with FFmpeg or similar tools for transcoding, segmenting and preparing media for AI models.

API & platform architecture

• Design and implement REST/gRPC APIs that expose AI model outputs (perception, multimodal alignment, narratives) to frontend and external systems.
• Define clear contracts for internal services and external integrations.
• Implement authentication, authorisation and rate‑limiting for platform endpoints.
• Ensure backward‑compatible API evolution as the product matures.

Model‑serving & AI integration

• Integrate with AI inference services (video models, multimodal models, LLM/VLM) running on GPUs or specialised infrastructure.
• Design request/response flows that handle large payloads, streaming outputs and structured results.
• Optimise throughput and latency for inference pipelines, including batching, caching and concurrency control.
• Collaborate closely with AI engineers to productionise models and debug end‑to‑end behaviour.

Storage, data models & performance

• Design data models to store embeddings, timelines, metadata, scene/shot boundaries, and narrative units.
• Work with appropriate storage technologies (SQL/NoSQL, object storage, search indices) based on access patterns.
• Implement indexing and query strategies for fast retrieval of segments, highlights and multimodal insights.
• Optimise performance for large datasets and high‑volume workloads.

Reliability, observability & operations

• Implement logging, metrics and tracing across services for debugging and monitoring.
• Set up health checks, circuit breakers and graceful degradation for critical services.
• Work with CI/CD pipelines to ensure safe, repeatable deployments.
• Collaborate on Kubernetes‑based deployments (or equivalent orchestration) for scaling services.

Requirements (must‑have)

Experience:

• 4–8 years in backend or platform engineering.
• At least 3 years working on distributed systems, high‑throughput services or complex pipelines (not just simple CRUD apps).

Languages & frameworks:

• Strong proficiency in Python or Node.js (one primary, both are a plus).
• Experience with at least one modern backend framework (FastAPI, Flask, Express, NestJS, etc.).

Distributed systems & pipelines:

• Hands‑on experience with queues and workers (e.g. Celery, RabbitMQ, Kafka, SQS, etc.).
• Experience building asynchronous, long‑running job pipelines.
• Understanding of idempotency, retries, backoff, and failure handling.

APIs & integration:

• Strong experience designing and implementing REST APIs (gRPC is a plus).
• Experience integrating with external services and handling network‑level failures.

Cloud & infrastructure:

• Experience deploying services on AWS, GCP or Azure (EC2/Compute Engine, S3/GCS, IAM, networking basics).
• Experience with Docker; exposure to Kubernetes is a strong plus.

Data & storage:

• Experience with SQL and at least one NoSQL store.
• Ability to design schemas and data models for performance and maintainability.

Engineering quality:

• Strong debugging skills across services and environments.
• Experience with unit/integration tests for backend systems.
• Clear, structured communication in English.

Nice‑to‑have

• Experience with media/video processing (FFmpeg, transcoding, segmenting).
• Experience with AI/ML model integration (serving models, handling inference requests).
• Experience with search/retrieval systems (e.g. Elasticsearch, vector databases).
• Experience with observability stacks (Prometheus, Grafana, OpenTelemetry).
• Experience working with remote teams across time zones.

What we are explicitly NOT looking for

To reduce noise and mismatches, we are not looking for:

• Pure CRUD‑only backend developers with no pipeline or distributed systems experience.
• Engineers who have only worked on small, single‑service apps without scale or complexity.
• Candidates who cannot explain trade‑offs in architecture, data modelling and reliability.
• Candidates who are uncomfortable with ownership of subsystems end‑to‑end.

Why join us

• Work on real, complex problems at the intersection of media, AI and distributed systems.
• Collaborate with senior AI engineers working on perception, multimodal fusion and narrative reasoning.
• Build the core platform that turns AI models into a usable product for broadcasters and media organisations.
• Operate with high ownership, clear expectations and direct access to the CTO.

Procedure is hiring for WorkHero.

WorkHero is building the AI-powered back office for the skilled trades, starting with the $50B+ HVAC industry. Small contractors are great at their trade but lose 20+ hours a week to invoicing, permits, scheduling, and paperwork. WorkHero combines expert office managers with automation and AI tooling, enabling a small team to take real ownership of that back-office work

We’re hiring a senior engineer to own our real-time voice stack end to end—AI agents operating on live phone calls—and the data platform that turns those calls into insight: call → transcript → events → warehouse → dashboards. You’ll own meaningful systems end to end alongside a small, senior team with deep experience in AI, product, and the trades.

What you’ll build

• New product screens and flows (jobs, customers, invoices, scheduling) in React and React Native, especially AI chat UI (chat & tool result rendering, streaming responses, human review and feedback loops)
• AI workflows in production: tool-using agents, RAG/search, classification/extraction, and human-in-the-loop flows
• Automations: Contribute new features and improvements to our AI-powered business automation platform

In addition, you’ll own our first investments into a realtime voice stack and the call-data platform behind it. For example:

• Realtime voice agents on live phone calls: telephony/WebRTC integration, streaming speech-to-text and text-to-speech, turn-taking, interruption handling, and latency optimization
• Voice pipeline reliability: backpressure, failover, graceful degradation, and monitoring for live calls
• Call-data pipeline: transcripts, events, and structured extraction flowing from every call into the warehouse
• Analytics & dashboards: data modeling and conversation-intelligence features on top of call data
• Evals & monitoring for voice agents: quality metrics, drift detection, and cost/latency tracking
• Cloud infrastructure: scaling our platform with infrastructure as code, queues and orchestration, and CI/CD

Responsibilities

• Analyze requirements and propose innovative AI-native solutions to technical problems
• Write clean scalable code
• Own the voice and data stack end-to-end: design, build, test, deploy, and operate
• Optimize the performance, latency, and cost of our real-time AI systems
• Respond to critical system issues and ensure continuous system reliability
• Mentor team members and collaborate across teams, especially with product and subject matter experts
• Work to understand the needs of our users and think creatively about how to solve design challenges in your work
• This is a Remote role. We expect a minimum 4 hours overlap with the WorkHero team (11 AM - 3 PM ET).

Qualifications

• Senior-level backend experience (typically 5+ years) shipping production systems that you've owned
• Hands-on experience with realtime voice or streaming systems: telephony (SIP/Twilio), WebRTC, streaming STT/TTS, or frameworks like LiveKit or Pipecat — or comparable experience with demanding realtime/streaming infrastructure
• Data engineering fundamentals: event pipelines, data modeling, warehousing, and analytics on production data
• Strong proficiency in a typed backend language (TypeScript preferred; comparable experience welcome)
• Hands-on experience with LLM-powered features (usage, prompting, optimization, etc) and AI architectures
• The ability to work with infrastructure as code (terraform), cloud, and CI/CD systems at scale. We're a small team, so we own the whole stack!
• Excitement to leverage AI coding tools to their maximum benefit. We love Claude Code and Cursor and are constantly looking for better ways to leverage our time to build fast and build for scale.

Nice to have

• experience with voice-AI platforms (Vapi, Retell, Bland, Deepgram, LiveKit) or conversation-intelligence products (e.g. Gong-style analytics)
• experience scaling cloud infrastructure, especially AWS, and how to get the most out of key AWS services
• experience with workflow automation tools like n8n or Lindy
• experience with React for building internal dashboards
• experience with HVAC or back-office business workflows

WorkHero is committed to building a diverse team. We encourage candidates from all backgrounds to apply.