Senior AI Engineer

Markit
London, UK
5 days ago
Apply on www.totaljobs.com
Prepare application

Role details

Contract type
Temporary to permanent
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Compensation
£182,000.0 - £234,000.0
Working hours
Regular working hours

Tech stack

Artificial Intelligence Amazon Web Services Automated Storage and Retrieval Systems Cloud Computing Encodings Communications Protocols Python (Programming Language) Language Modeling Open Source Technology OpenShift Open Web Application Security Software Engineering
+18 more
Systems Integration Data Ingestion Large Language Models Multi-Agent Systems Software Security Model Validation Generative AI Indexer Git SC Clearance Build Management Kubernetes Low Latency Deployment Automation Production Code Machine Learning Operations Data Pipelines Docker

Job description

The business is looking for a Senior Applied AI Engineer to take genuine technical ownership of the design and delivery of production-grade agentic AI systems.

This is a builder’s role rather than an integration role. You will design and implement systems from the ground up, make architecture-level decisions, write production-quality code and own features through to deployment.

The systems you build will operate in environments where reliability, security and trust are critical. You will therefore be expected to engineer for real-world conditions, including high workloads, degraded connectivity, secure infrastructure and fully offline or air-gapped deployments. What You’ll Be Doing

  • Design and build multi-agent AI systems from the ground up, using frameworks such as LangGraph, LangChain, Haystack or similar where appropriate.
  • Develop the orchestration, state management and tool-calling infrastructure required to make agentic systems reliable in production.
  • Integrate large language models and vision-language models into reasoning, retrieval, summarisation and task-execution pipelines.
  • Build retrieval, memory, evaluation and guardrail capabilities around AI systems.
  • Design and implement production pipelines covering data ingestion, processing and inference.
  • Work with large-scale multimodal datasets spanning text, imagery, telemetry and sensor data.
  • Design indexing, embedding and retrieval systems capable of operating across multi-terabyte datasets.
  • Deploy AI systems across cloud, on-premises, sovereign and fully offline environments.
  • Engineer for reliability, latency, security and predictable failure behaviour.
  • Build evaluation and observability capabilities to understand model performance, agent behaviour and failure modes.
  • Take end-to-end ownership of technical workstreams, from architecture through deployment.
  • Establish engineering patterns and technical direction for other engineers.
  • Produce clear technical documentation and knowledge transfer to ensure systems can be maintained beyond the engagement.

Requirements

You’ll ideally have:

  • 6+ years of professional software engineering experience, with several years working on LLM-based, generative AI or agentic systems.
  • A strong track record operating at Senior, Lead or equivalent engineering level.
  • Commercial experience building multi-agent or agentic AI systems for production, rather than simply integrating existing tools.
  • Strong Python development skills and excellent software engineering fundamentals.
  • Hands-on experience with frameworks such as LangGraph, LangChain, Haystack or similar, together with the ability to work below the framework level when required.
  • Experience designing and deploying AI/ML systems into genuine production environments.
  • Strong understanding of model inference, latency, performance, data pipelines, state, memory and tool/function calling.
  • Experience building search and retrieval systems over very large multimodal datasets.
  • Experience with Docker, Git and cloud platforms, ideally AWS.
  • Understanding of secure deployment architectures, including air-gapped, on-premises or sovereign cloud environments.
  • The ability to take technical ownership, make sound systems-level decisions and deliver dependable production software.
  • Strong communication skills, with the ability to explain complex technical concepts to both technical and non-technical stakeholders.

Desirable Experience

The following would be advantageous:

  • Multimodal AI and reasoning.
  • Edge or offline AI deployments.
  • Kubernetes, particularly EKS or OpenShift.
  • MLOps, including model evaluation, monitoring and reproducibility.
  • Observability for agentic AI systems, including model performance, agent behaviour and drift.
  • Agent orchestration and inter-agent communication protocols such as A2A.
  • Model Context Protocol (MCP).
  • Secure-by-design development principles, including ISO 27001, NIST or OWASP.
  • Experience within defence, national security or other highly regulated environments.
  • Contributions to open-source AI/ML projects.

Security Clearance

Due to the nature of the work, applicants must be eligible to obtain UK security clearance.

Candidates will generally need to:

  • Hold a UK passport.
  • Have 5 years of continuous UK residency.
  • Be eligible for BPSS and SC clearance.

Clearance sponsorship may be considered for the right candidate. However, given the contract nature of the position, candidates who already hold active, transferable SC clearance are strongly preferred.

DV clearance would be an advantage., If you are a senior engineer who enjoys building sophisticated AI systems from first principles and wants to see your work deployed in environments where reliability and accuracy genuinely matter, we’d like to hear from you.

About the company

This is an opportunity to work on genuinely challenging AI problems where engineering quality matters.

You will:

  • Own AI systems end-to-end rather than simply delivering individual tickets.
  • Work at the forefront of agentic and generative AI.
  • Shape architecture and engineering practices.
  • Work with large-scale, multimodal data and complex AI pipelines.
  • Deploy systems into demanding real-world environments.
  • Work alongside a highly technical, fast-growing team.
  • Have the potential for an extension or longer-term engagement.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.totaljobs.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:08 min

Essential engineering roles in the generative AI space

Mary Grygleski Mary Grygleski · LIVE

6:21 min

Investigating push inefficiencies with upstream Git experts

Jonathan Creamer · Coffee With Developers

2:07 min

Inspecting default bridge architectures and custom Docker networks

Oliver Seitz Oliver Seitz · World Congress 2025

2:36 min

Analyzing limitations with PostgreSQL bitmap heap scans

Dharin Shah Dharin Shah · World Congress 2025

3:22 min

Evaluating advanced artificial intelligence platforms for daily recruitment

Rudi Bauer Rudi Bauer +1 · Cappuccino with HR

56 sec

Favorite git commands and the importance of patch commits

Eileen Uchitelle Eileen Uchitelle +1 · Coffee With Developers

Videos

See all

Related articles

See all