Senior AI Engineer

Condukt; Greater London; Ibrido; GBP 90.000 - 150.000; Tempo pieno

Vantaggi offerti da questo lavoro

Equity package

Porto office, 3 days/week

Flat hierarchy

Top-of-the-line equipment

Private health insurance

Sick leave

Descrizione del lavoro

Condukt, a London-based early-stage compliance platform, seeks a Senior AI Engineer to own data pipelines connecting models to product and to build robust, production-grade AI systems. You will ship code frequently, iterate quickly, and collaborate with ML and backend engineers to turn prototypes into reliable services while meeting security and uptime requirements.

Join a fast-moving team with a track record of growth, where you define standards, build scalable infrastructure, and contribute to

Competenze

• 5+ years as software/data/ML engineer in product-centric settings.
• Experience in production-level Python and building backend services and APIs.
• Experience integrating LLMs in production and handling their practical limits: context windows, cost, latency, and non-determinism.
• Experience building agent harnesses and multi-agent, autonomous agent, or agent-to-agent systems in production.
• Experience setting up evaluation and metrics for AI systems, and using them to make decisions.
• Familiarity with MLOps practices, containers, CI/CD, and at least one major cloud platform.
• Bachelor's or Master's degree in Computer Science or a related field.
• Excellent communication skills and ability to work collaboratively in a fast-moving environment.

Mansioni

• Own the data pipelines behind the AI platform end to end.
• Build the context management layer for agents and LLMs.
• Develop agent harnesses and the agent loop, tool calling, context assembly, guardrails and tracing.
• Design multi-agent and autonomous agent systems and reliable agent-to-agent interfaces.
• Develop evaluation pipelines and production metrics for LLM and data quality.
• Run and harden LLM integrations in production with fallbacks, rate limiting, caching and observability.
• Set up MLOps with CI/CD for ML components, versioning and safe rollouts.
• Collaborate with ML and backend engineers to turn prototypes into reliable production services.
• Continuously improve engineering, data, and AI practices and define standards and tooling.

Conoscenze

Python

Backend services

LLMs in production

Agent harnesses

MLOps practices

CI/CD

Cloud platforms

Communication skills

Formazione

Bachelor's or Master's in Computer Science

Bachelor's or Master's in CS

Strumenti

Docker

Kubernetes

AWS

GCP

Azure

Git

Descrizione del lavoro

About us

Condukt is the next-generation compliance platform for financial services, offering an agentic solution powered by real-time data for business identity.

Always-on and policy-aware, the company enables financial institutions and fintechs to gain actionable insights into business verification - unlocking growth, increasing efficiency, and strengthening compliance.

We were founded by former operators and builders with deep experience in banking, payments, and lending. Today, our team spans across London and Porto, bringing together engineers, product owners, and operators from companies like Revolut, Meta, Block (Square), SumUp, American Express, Yandex, and OakNorth.

Trusted by leading regulated entities, including Wise, Tide, Mollie, Shift4, Flatpay, and myPOS, the company is backed by top investors, including Lightspeed Venture Partners and MMC Ventures.

Position Overview

We are looking for a Senior AI Engineer to join our team. You will own the systems that connect our models to our product: the data pipelines that feed them, the context they work with, the multi-agent systems they run in, and the metrics that tell us whether they work. You'll set the standards and patterns our team builds on and work closely with our ML and backend engineers to take AI functionality from prototype to reliable, production-grade systems.

As an early-stage startup, we pride ourselves on our ability to roll up our sleeves and build from scratch. You’ll ship code frequently, iterate quickly based on feedback, and still meet the stringent security, performance, and uptime requirements our clients expect.

We all love to build, scale, and grow: our leadership team has a strong track record of building products, scaling teams, and driving growth, and our ambitious engineers join us from leading tech companies and unicorns.

If you’re passionate about building the foundations that make AI products reliable, measurable, and fast to iterate on, this role is for you. You’ll have a meaningful opportunity to shape our engineering culture from the ground up.

What you'll do

Own the data pipelines behind our AI platform end to end, turning register data and web content into parsed, structured data with a full audit trail and strong data-quality checks

• Build the context management layer that decides what our agents and LLMs see, balancing relevance, token budgets, memory, and cost

• Build the harnesses our agents run in: the agent loop, tool calling, context assembly, guardrails and tracing

• Design and build multi-agent and autonomous agent systems, including the agent-to-agent interfaces that let our agents hand work to each other reliably

• Develop evaluation pipelines and production metrics for LLM and data quality, so every change to a model, prompt, or pipeline can be measured before and after it ships

• Run and harden our LLM integrations in production, with robust fallbacks, rate limiting, caching, cost tracking, and observability

• Set up MLOps practices such as CI/CD for ML components, versioning of prompts, models, and datasets, and safe rollouts

• Work closely with ML and backend engineers to turn prototypes into reliable production services with clean interfaces

• Continuously improve our engineering, data, and AI practices, helping define standards, processes, and tooling that align with industry best practices

What you bring

You are an effective and self-driven builder who enjoys working across the boundary between ML, backend engineering, and DevOps

• 5+ years of experience as a software, data, or ML engineer in product-centric settings

• Experience in production-level Python and building backend services and APIs

• Experience integrating LLMs in production and handling their practical limits: context windows, cost, latency, and non-determinism

• Experience building agent harnesses and multi-agent, autonomous agent, or agent-to-agent systems in production

• Experience setting up evaluation and metrics for AI systems, and using them to make decisions

• Familiarity with MLOps practices, containers, CI/CD, and at least one major cloud platform

• Experience self-hosting open-weight models is a plus

• Bachelor's or Master's degree in Computer Science or a related field

• Excellent communication skills and ability to work collaboratively in a fast-moving environment

Our Offer

Tackle meaningful problems with real-world impact

• Competitive salary and equity package

• Join us in our Porto office, minimum 3 days a week

• Flat hierarchy with direct access to founding team

• Top-of-the-line equipment

• Private health insurance, plus sick and compassionate leave as needed