Senior Python Backend Engineer (AI / Agents)

General

Full time

Remote

About Vidrush

Vidrush is building a modern AI-powered product that helps creators produce high-quality videos faster. We combine LLM-driven workflows with video intelligence to automate the hardest parts of creation — while keeping the user in control.

We’re early-stage, moving fast, and hiring engineers who want real ownership and direct impact.

The Role

We’re looking for an AI Engineer to build and ship production-grade agentic workflows and video intelligence modules. You’ll work on systems that combine LLMs, tools, and media understanding to solve real product problems.

This is a hands-on engineering role: you’ll prototype quickly, harden what works, and deploy scalable pipelines into production.

What You’ll Do

  1. Build agentic systems that can reason, plan, and execute multi-step tasks reliably
  2. Design and deploy LLM-based services (tool use, structured outputs, evals, monitoring)
  3. Develop video/image intelligence pipelines (retrieval, matching, classification, metadata extraction, generative augmentation)
  4. Integrate existing APIs and tools when appropriate (strong build-vs-buy judgment)
  5. Ship scalable inference pipelines on cloud infrastructure
  6. Apply MLOps / LLMOps best practices: observability, testing, evals, versioning, cost control
  7. Work closely with founders and product to iterate quickly based on user feedback

What We’re Looking For

  1. Strong Python engineering skills and proven ability to ship production systems
  2. Experience building with LLMs (OpenAI-style APIs, tool calling, RAG, structured generation)
  3. Experience deploying ML/LLM services in production (cloud, containers, serverless, async pipelines)
  4. Practical understanding of video/image processing (CV or media pipelines)
  5. High autonomy: you can take vague problems and turn them into shipped solutions
  6. Strong engineering fundamentals: clean code, reliability, performance, and cost awareness

Nice to Have

  1. Agent orchestration frameworks (LangGraph, LangChain, AutoGen, CrewAI, etc.)
  2. Experience with vector search / embeddings / retrieval systems
  3. Experience with workflow orchestration (queues, batch jobs, event-driven systems)
  4. Experience with PyTorch and GPU inference optimization
  5. Experience working on media-heavy products (video editing, video generation, large file pipelines)

How We Work

  1. Small team, high trust, high ownership
  2. Bias to action and shipping
  3. Lightweight specs, fast iteration
  4. Strong focus on developer experience, testing where it matters, and observability

Apply

Send:

  1. GitHub / portfolio (if available)
  2. a short note on relevant projects (agents, LLM workflows, video pipelines)
  3. your timezone + availability