Senior AI Software Engineer

ExTrac; Greater London; Sur place; GBP 90 000 - 130 000; Plein temps

Résumé du poste

ExTrac is seeking a Senior Software Engineer to join the AI team, building Co-Analyst and the analytical AI features around it. You will own services end to end across a Python and Go codebase, collaborating with the data team for ingestion pipelines and a research-focused ML team for model integration.

In this role you will work on agent orchestration, retrieval, graph analytics, and long-running streaming pipelines, while ensuring production-grade performance and reliability in a fast-paced

Qualifications

• Built and operated production backend systems.
• Experience designing and consuming APIs.
• Strong sense of data and databases in production systems.

Responsabilités

• Own services end to end in Python and Go.
• Design APIs used by internal teams and customers.
• Maintain latency, cost, and reliability of agent workflows.
• Contribute to system design and architecture decisions.

Connaissances

Python

Go

Backend systems

APIs

Database design

Description du poste

About ExTrac

ExTrac is a decision intelligence company used by governments, defence organisations, financial institutions, and corporates operating in complex, fast-moving environments. Our capabilities fuse curated data sources, domain-specific AI, and deep human expertise to transform information overload into clear, actionable foresight.

About ExTrac

ExTrac is a decision intelligence company used by governments, defence organisations, financial institutions, and corporates operating in complex, fast-moving environments. Our capabilities fuse curated data sources, domain-specific AI, and deep human expertise to transform information overload into clear, actionable foresight.

About ExTrac

ExTrac is a decision intelligence company used by governments, defence organisations, financial institutions, and corporates operating in complex, fast-moving environments. Our capabilities fuse curated data sources, domain-specific AI, and deep human expertise to transform information overload into clear, actionable foresight. Our ambition is to become the analytical backbone that organisations rely on when geopolitical uncertainty becomes an opportunity or a strategic risk. More at extrac.ai.

The Role

We are looking for a Senior Software Engineer to join ExTrac's AI team, building Co-Analyst and the analytical AI features around it. Co-Analyst is a user-facing multi-agent system that works alongside intelligence analysts to research and write reports. A planning loop decomposes an analyst's question, fans work out to sub‑agents, and assembles the results into a report where every claim traces back to the chunk of source it came from. Underneath sits vector search over a large unstructured corpus, across multiple languages and media types. The agent work is the centrepiece but not the whole job. In a single quarter the work spans agent orchestration, retrieval, graph analytics, and long‑running streaming pipelines, alongside the services and databases underneath them. You will own services end to end across a Python and Go codebase, working alongside the data team who own the ingestion pipelines and a research‑focused ML team who train and evaluate the models we integrate and serve. The loop is short: product brings an idea, often recent and unproven, and our job is to spike an implementation and take it to a production feature. New features land close to weekly. This hire exists to raise the AI team's throughput on hard problems, with an engineer who brings the systems depth to take an AI capability from something that works to something analysts can rely on.

What The Job Involves

Agentic and analytical AI features

• Build and improve the agent loop itself: context assembly, tool selection, and sub‑agent orchestration.
• Build the analytical AI features that sit alongside it, from network construction through to the summaries analysts read.
• Prove that changes are improvements, running experiments against live analyst traffic behind feature flags.
• Agree what "better" means for a capability before shipping it, and make the call honestly when the evidence says a promising approach is not working.
• Find workable approaches where no established pattern fits, on a dataset that rarely arrives clean.
• Work with embeddings as more than a retrieval concern. The same vectors drive network construction and community detection.
• Work within a model‑agnostic design, swapping models and embeddings on the back of the ML team's evaluations rather than being locked to one.

Service design and delivery

• Take an ambiguous problem, gather requirements, write a technical design, and ship to production with minimal oversight.
• Own services end to end, including consolidating or decommissioning what they replace.
• Design APIs used by both internal teams and customers, and hold them to clear contracts and sensible versioning as the number of consumers grows.
• Treat the storage layer as a design concern rather than an implementation detail: schema, indexing strategy, and access patterns, across relational, document, and vector stores.
• Contribute to and lead system design and architecture decisions.

Production engineering

• Own supporting services end to end across Python and Go: design, build, deploy, operate.
• Hold agent workflows to production standards for latency, cost, and reliability, in a system where non‑determinism is a given.
• Build and operate long‑running streaming pipelines, including the caching and recovery behaviour that makes them survivable.

Working with analysts, product, and the ML team

• Work directly with the analysts who use our products, turning what they hit in practice into changes in the system.
• Iterate quickly against a live stream of product requests, flagging where they collide with longer‑horizon capability work.
• Partner with the ML team on agentic approaches, taking proven concepts to production and solving the engineering, performance, and reliability problems a research implementation does not have to.
• Integrate and serve the models they train, and build the production infrastructure their evaluation frameworks run on.

You should apply if

• You have built and operated production backend systems, and you want to keep doing that. You know the difference between something that demos well and something that holds up under production load, latency, and cost.
• You will spend more of your time in Python and Go services, databases, and APIs than in a prompt file.
• You can operate with a high degree of autonomy. You will be trusted to lead projects, make decisions, and drive outcomes. We work on open-ended problems with no established answer, and when the obvious approach fails you generate alternatives rather than stopping.
• You have opinions about agentic frameworks and are comfortable not using one. Experience with them is useful, but we build most of our own orchestration, because off‑the‑shelf abstractions have not survived our