Company Description

Imaginario AI is building a video intelligence layer that powers content discovery and storytelling for marketing and post-production teams in video-heavy industries. The company focuses on unlocking insights from video to help teams work faster, create more effective content, and streamline workflows.

Imaginario AI collaborates with forward-looking creative and media organizations that rely on rich video libraries. The company has been recognized with the IABM BaM Awards for Content Management and Best of Show at IBC in both 2024 and 2025, highlighting its innovation and impact in the media technology space.

What we're looking for

Imaginario AI is looking for a Senior Agentic AI Engineer who has built and shipped LLM-powered systems in production and cares about making them accurate, reliable and affordable at scale. You specialize in LLM and agentic pipelines, and you are also a capable full-stack engineer who can take a feature from backend service to user interface.

You will join a small, senior team and work closely with our engineering and product leadership to build the agentic layer of our video intelligence platform: agents that search, reason over and assemble video using our shot-level index, retrieval pipelines that ground every answer in real evidence, and MCP integrations that let AI assistants and third-party tools work directly with our customers' video libraries.

This is a hands-on build role, not a research role. We care about what you have put in front of real users, how you measured it and what you changed when it went wrong.

What you will do

Agentic pipelines

• Design, build and run multi-step agentic workflows in production: planning, tool and function calling, routing, and orchestration across several tools and data sources.
• Coordinate several specialized agents that hand work back and forth, not only in a fixed sequence.
• Make agents dependable with structured outputs, schema validation, retries, timeouts, fallbacks, guardrails and human-in-the-loop steps where the stakes call for them.
• Build long-running agents with durable execution: checkpointed state, resume after failure, pause for user input, and branching to try alternative versions.
• Keep agents fast and cost-efficient by tracking latency, token usage and cost per task, and by choosing the right model for each step.

Context and memory management

• Own context engineering: decide what goes into the model's context at each step, where it comes from and what gets cut when the budget is tight.
• Compress and summarize long inputs such as hour-long transcripts and dense shot-level metadata without losing the facts that matter.
• Build memory for agents and users: short-term session state, long-term memory across sessions and projects, and clear rules for what persists, what is retrieved and what is pruned.

Retrieval-augmented generation (RAG)

• Build and improve RAG over multimodal video metadata, including transcripts, shot descriptions, entities, topics and chapters.
• Own the full retrieval stack: chunking strategy, embeddings, hybrid search (dense plus keyword), metadata filtering, query rewriting and reranking.
• Diagnose retrieval failures and fix them at the root, whether the problem is in ingestion, indexing, ranking or generation.

MCP and integrations

• Build and maintain MCP servers that expose Imaginario's search, indexing and assembly capabilities to AI assistants and external agents, including tool design, schemas, async jobs with clear progress and status responses, authentication, rate limits and versioning.
• Integrate third-party tools and data into our agents through MCP clients, REST APIs and webhooks, including media storage, MAM/DAM and editing systems.

Agentic web search

• Integrate third-party web search and agentic search APIs into our pipelines, for example to enrich asset-level metadata with trusted external information.
• Handle source selection, freshness, deduplication and citation, and combine web results with internal retrieval so answers stay grounded and traceable.

Accuracy, hallucination reduction and evaluation

• Reduce hallucinations and improve accuracy with grounding and citation enforcement, verification and self-critique steps, constrained generation, and the ability to abstain when the evidence is weak.
• Build our evaluation harness: golden datasets, retrieval metrics (recall, precision, MRR), faithfulness and answer quality checks, and LLM-as-judge scoring calibrated against human review.
• Evaluate agent trajectories as well as outputs: tool choice, number of steps, cost and latency per task.
• Run evals as regression tests on every release, and add tracing and observability in production so issues are caught by us before customers see them.
• Turn user edits, ratings and accept or reject signals into better outputs over time, through rubrics, example-based context and eval sets.
• Write clear documentation and share what you learn with the rest of the team.

Full-stack delivery

• Build features end to end, from Python backend services and APIs to the React interfaces where users work with agents, search results and assembled video.
• Contribute to the reliability, performance and security of the wider platform, including services, background workers and cloud infrastructure.

What you might work on in your first six months

• Agentic workflows on top of our video index that turn a natural-language brief into searches, shot selections and an assembled first cut.
• Our MCP connector, so customers can search and work with their video libraries from the AI assistants they already use.
• An evaluation harness that tracks retrieval quality and hallucination rate across releases.
• Agentic web research that enriches asset summaries with verified third-party title and entity information.

Requirements

• 5+ years of professional software engineering experience, including at least 3 years building LLM-powered applications that real users relied on in production.
• Shipped at least one RAG system to production, ideally combining internal retrieval with web or agentic search and citing its sources, and can walk us through what you measured and what you changed to improve retrieval quality and reduce hallucinations.
• Hands-on experience building agentic systems with tool calling, multi-step workflows and long-running state, including context window and memory management, using frameworks such as LangGraph, LlamaIndex or similar, or your own orchestration code. You know when a framework helps and when it gets in the way.
• Experience building or integrating MCP servers or clients, or comparable tool and API integrations for LLM agents.
• Solid knowledge of embeddings, vector databases and search engines (for example pgvector, OpenSearch, Elasticsearch or Qdrant) and rerankers.
• An evaluation mindset: you have built eval sets and metrics and used them to make decisions, not just to report numbers.
• Experience working with both commercial LLM APIs and open-weight models, and comparing them on quality, latency and cost.
• Strong Python for backend services and APIs (Flask, FastAPI or similar), including async code, testing and microservices.
• Hands-on React experience (JavaScript or TypeScript) building production user interfaces, and a track record of shipping features end to end, not only AI components.
• Working knowledge of cloud infrastructure (AWS preferred), Docker, CI/CD and background task queues.
• Professional working proficiency in English, our working language, and clear written communication.

Nice to have

• Experience with multimodal data such as video, speech transcripts or images.
• Experience with timecode, frame-accurate trimming, FFmpeg, or edit formats such as EDL, FCPXML or OpenTimelineIO.
• Background in media, entertainment, news or sports content.
• Experience with LLM observability and tracing tools such as Langfuse, LangSmith or OpenTelemetry.
• Experience applying reinforcement learning or other feedback-driven methods to improve model or agent output.
• Experience with fine-tuning, prompt optimization or structured information extraction at scale.
• Experience deploying and serving open-weight models, for example with vLLM or similar.
• Experience building desktop or on-device apps, such as editing-software plugins (for example Premiere Pro panels), local MCP servers, or running models locally.
• Previous experience in an early-stage startup where you owned features end to end.
• Open-source contributions, talks or writing about agents, RAG or evaluation.

Benefits

• Fully remote work
• Flexible working hours
• Private health insurance
• 15 days of paid annual leave per year (in addition to public holidays)

About Us

Imaginario AI is an AI-powered video intelligence platform for media, entertainment and corporate teams. Through our API and platform, customers search inside their videos, understand them at the shot level and assemble new content faster, without writing a single line of code.

We are backed by Comcast and Techstars, part of NVIDIA Inception, and have won the IABM BaM Award in Content Management, Best of Show at IBC twice, and IABM Mediatech Start-Up of the Year.

We are an equal opportunities employer and we positively encourage applications from suitably qualified and eligible candidates regardless of sex, race, disability, age, sexual orientation, gender reassignment, religion or belief, marital status, or pregnancy and maternity.