Research Engineer - Harness Engineering and Agentic Orchestration

About Tessl

AI is transforming how software is built, and at Tessl, we're building the infrastructure for what comes next.

We're developing a platform that enables engineering teams to build and run AI-powered software factories, where coding agents take on real development work, from picking up engineering tickets to implementing changes and creating pull requests.

By combining structured context, reusable agent skills, automated workflows and evaluations, we're making AI-powered development more reliable, repeatable and scalable, while keeping humans in control. We're tackling some of the biggest challenges in autonomous software development, from code quality and security to helping organisations confidently adopt AI agents at scale.

Founded by Guy Podjarny, previously founder of Snyk, Tessl is a fast-growing Series A startup backed by over $100 million in funding from investors including Index Ventures, Accel, GV and Boldstart.

Joining Tessl means helping define an entirely new category of technology, solving ambitious technical challenges and shaping the future of software development.

Overview of the role

We're hiring a Research Engineer to join our AI Research (AIR) team. You'll work on the components that make the outer loop real: how agent harnesses orchestrate model behaviour, how we evaluate what's actually working, how pipelines turn production traces into the next round of improvement, and how we diagnose the failure modes that matter to real users.

These aren't four separate workstreams — they're parts of one system, and we want people who see them that way.

We expect you to sit close to customers — joining calls, watching sessions, reading traces — and to let real workflows shape your research priorities. You'll have meaningful autonomy and the resources to run substantial experiments where the bar for success is shipped impact.

You'll report to our AI Research Lead, and collaborate closely with engineering, product, and design.

What we're looking for

We're explicitly building coverage across four skill areas. You don't need to be strong in all of them — but you should bring depth in at least one:

• Agent harness and orchestration design — how tools, context, and control flow combine to make a useful agent.

• Agentic eval methodology — task and repo-level evals, dataset curation, the craft of measuring what actually matters.

• Outer-loop and pipeline thinking — feedback loops, training-data flywheels, bandit-style optimisation, anything that goes beyond a single agent session.

• Failure-mode analysis — instrumenting agents, reading traces at volume, surfacing patterns engineering can act on.

Essential

• 4+ years shipping AI/ML products in a startup or applied industry setting, with recent hands-on experience with LLMs and agentic systems.

• Demonstrated depth in at least one of the four skill areas above.

• Strong product and customer instincts: comfort joining customer calls, watching session recordings, and letting real workflows shape what you work on.

• Sharp evaluation judgement: benchmarks where they exist, vibes and quick prototypes where they don't, and the taste to know which is appropriate.

• Experience building datasets for evaluation or training, including the pipeline work that goes with it.

• Deeply curious about agents and excited about reshaping how software is built.

Nice to have

• A Masters or PhD in a relevant computational field.

• Direct experience with coding agents or code-generation systems.

• Background in RL, bandits, or other outer-loop optimisation frameworks applied to LLMs.

• Experience building synthetic data, dataset infrastructure, or internal tooling that other engineers actually used.

• A project you can show us (GitHub links welcome) and a thoughtful answer to "Why Tessl?"

What you'll do

No two weeks will look the same. A flavour:

• Sit in on a customer session, understand how their agents are failing, design an eval that captures it, and drive a fix through to shipped improvement.

• Close a piece of the outer loop end to end: production signal in, dataset out, eval scored, harness change shipped, metric moved.

• Own a slice of our eval infrastructure: dataset curation, harness configuration, runner, analysis, and the comms back to engineering.

• Prototype a new harness or context configuration and measure whether it actually moves the needle on real customer tasks.

• Dig through pages of agent traces, build the tooling you need to make sense of them, and brief the team on what you found.

• Partner with product and engineering on near-term shipping problems by bringing research rigour.

• Pull a recent paper apart, work out what's actually transferable to our platform, and turn it into a concrete experiment.

You’ll be successful if…

In your first 3 months, you might have shipped a new eval suite for a real customer workflow, improved an agent harness based on trace analysis, or built a pipeline that turns production failures into reusable test cases.

Application process

• Intro call to understand "Why Tessl?" and to tell you a bit about us.

• A call with our AI Research Lead to understand your ways of working and how you use agents.

• A 4 hour technical take-home exercise extending our one-shot implementation.

• A half-day on-site session including whiteboarding and hands-on activities.

• Leadership chats with our Head of People, Head of Engineering and CEO.

Life at Tessl

We want Tessl to be a place where you can do meaningful work, keep learning and enjoy being part of the team. Alongside competitive compensation, we offer benefits designed to support you both inside and outside work.

What we offer

• Competitive compensation and equity: Market-benchmarked salaries and EMI share options.

• Time off: 25 days of annual leave, plus UK public holidays, and two paid volunteering days each year.

• Private healthcare: Vitality medical insurance, including dental, optical and mental health support, with cover included for partners and dependants.

• Pension: A 5% employer pension matched contribution through Smart Pension.

• Life assurance: Company-paid life insurance with MetLife providing cover of four times your annual salary.

• Family Leave: We offer enhanced Maternity, Parental and Adoption Leave from day one to support you and your growing family.

• Learning and development: We support opportunities to continue developing your skills with a £1,000 per year to spend.

• Commuting benefits: Financial support for eligible team members commuting from outside Greater London, plus a Cycle to Work scheme.

• Summer & winter offsites: Twice a year, we bring the whole Tessl team together for a week-long offsite. It's a chance to step away from our usual routines, collaborate on big ideas, build stronger relationships and enjoy shared experiences together. And of course, we have a lot of fun along the way!

Our London HQ

Our office is in the heart of King's Cross, surrounded by London's growing AI and technology community.

We work together in person on Mondays, Tuesdays and Thursdays, giving us time to collaborate, exchange ideas and build relationships. You'll also enjoy catered lunches (Tuesday & Thursday), plenty of office snacks, regular team lunches and socials, plus a pet-friendly workplace.

How we work

Our operating principles shape how we collaborate and make decisions. We move quickly and learn by doing, build on ideas before challenging them, get stuck in wherever we can help, and give people real ownership. We encourage thoughtful debate, curiosity and a willingness to try things that haven't been done before. Read our five operating principles.

We're AI native

AI isn't just what we're building - it's central to how we work every day, across every function. We actively use AI to improve how we work, solve problems and challenge traditional ways of doing things.

You don't need to be an AI expert to thrive at Tessl, but you do need curiosity, an appetite for experimentation and a willingness to embrace new ways of working. We expect everyone to use AI regularly, invest time in learning how to get the most from it and keep experimenting when something doesn't work the first time, rather than defaulting to manual approaches.

We're also big believers in sharing what we learn. We encourage transparency about how we're using AI, what's working, what isn't and how we can help each other improve. Being AI native doesn't mean removing human judgement, it means using AI thoughtfully, while taking ownership of the quality and outcomes of our work.

Everyone is welcome at Tessl

We're committed to building an inclusive environment where people from different backgrounds, experiences and perspectives can thrive.

We particularly welcome applications from people who are underrepresented in technology. If you're excited about the opportunity but don't meet every requirement, we'd still encourage you to apply.

If you need any adjustments or additional support during the recruitment process, please let us know. We're happy to work with you to make the process accessible and comfortable.

Come build with us

We're moving fast, experimenting boldly and figuring things out as we go. There's plenty to build, lots to learn and real opportunities to make your mark.

If you're excited by big ideas, enjoy getting stuck in and want to be part of something from the ground up, we'd love to hear from you!