Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
BoltzPosted in November 2026

Research Engineer, Agents

Remote · King's CrossRemoteFull-time
Who we'd reach at BoltzFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Talent partner

Hires for this team

Senior teammate

On the team, can refer you

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a full-time research engineering role at Boltz, open to remote candidates or those based in King's Cross, London. The role suits a systems engineer who has built agent systems and understands where current frontier language models succeed and fail. You will design and own the agent harnesses that power scientific research at the company, covering tool use, orchestration, and state management. Work is done with researchers across teams, with the aim of making pipelines reusable and scaling them across a shared compute cluster. Prior machine learning research experience is not required.

What you’ll do

  • Design and build agent harnesses covering tool use, orchestration, and context and state management.
  • Work with researchers to build agentic pipelines and tooling, and make them reusable across teams.
  • Scale harnesses to support large numbers of agents running on the cluster.
  • Build observability, verification, and cost controls for large agent runs.
  • Evaluate agent setups rigorously and keep harnesses current as frontier models change.

What they’re looking for

  • Strong software engineering background, including distributed systems or infrastructure running many long-running parallel jobs.
  • Hands-on experience building agent systems or harnesses that you can discuss in depth.
  • Solid judgment on the capabilities and failure modes of frontier language models.
  • A record of tools adopted by researchers or engineers.

Nice to have

  • Experience building open-source agent harnesses or extending existing ones.
  • Understanding of LLM architectures and fine-tuning via SFT or reinforcement learning.
  • Background in NLP or information retrieval.
  • Experience running workloads on shared compute or cloud infrastructure such as Kubernetes.
  • Exposure to scientific research workflows or prior use of Boltz models.

What’s on offer

  • Highly competitive salary with meaningful equity in a public benefit company.
  • 25 days annual leave plus bank holidays.
  • Private healthcare (BUPA) covering pre-existing conditions, and a pension program.
  • Paid parental leave, gym membership, free daily lunch, and travel expenses.
  • Annual team offsite.

Skills

Questions about this role

Is this role remote?

The role is listed as remote, with a King's Cross, London location also available.

Do I need an ML research background?

No. The posting states that an ML research background is not needed.

What kind of experience is required?

Strong software engineering experience, including distributed systems, and hands-on experience building agent systems.

What benefits are offered?

Equity, 25 days leave plus bank holidays, private healthcare, pension, parental leave, gym membership, and daily lunch.