×
Laminar
Open-source AI agent observability platform
Last verified August 17, 2026 · Updated daily
What Laminar is building
AI agents don't fail cleanly. They run for 40 minutes, make 200 decisions, and crash in a way that a tree of spans can't explain. Laminar is the observability layer built for that. With one line of code, it captures every LLM call, tool use, and function execution across a long-running agent session. For browser agents, it syncs screen recordings directly to traces so you can see what the agent was looking at when it made a bad decision. Its 'Signals' feature uses AI to surface failure patterns across sessions automatically, turning raw traces into a feedback loop. The product is open-source and already the default observability tool in Browser Use's documentation and OpenHands' benchmarking infrastructure.
Why this matters
The observability category was built for simple request-response LLM calls. Every major tool in the space, Datadog, LangSmith, Langfuse, was designed for chains that terminate in milliseconds. But the wave that's actually arriving is autonomous agents: pipelines that run for tens of minutes, spawn subagents, interact with browsers, write code, and fail non-deterministically. That's a fundamentally different debugging problem. Laminar is the first company purpose-built for it, and they already have real traction: Gusto, Browser Use, OpenHands, and Alai are live customers. The angel roster is deliberately strategic here. Ben Sigelman is the co-creator of OpenTelemetry, the standard that governs how observability data is generated and exported across the software industry. His bet on Laminar is a signal that agent-native observability is about to become a standards conversation, not just a tooling one.
Open roles at Laminar
3 positions we're tracking. Roles are re-checked daily and removed when filled.
Know when Laminar is hiring before anyone else
A role stays uncontested for about four days. Here's the window — and where we put you in it.
From $9/month, cancel any time.
Watching Laminar
0 applicantsRole spotted & verified
1You get the alert
1You've applied
~8Hits the job boards
250+Working at Laminar
Since , Laminar has built Open-source AI agent observability platform. The team is now <50 people. For a B2B, Engineering, Product and Design company this size, the reality is broad remit, direct access to founders, and equity that still means something if the company works out.
The majority of roles are in London.
How to actually get hired at Laminar
Why applying the normal way doesn't work
At <50 people, Laminar has no recruiting team. Your application lands with a founder who is also running sales, product and payroll. The obstacle isn't a queue or an ATS, it's being seen at all. Cold outreach outperforms the form here, consistently.
Who to contact at Laminar
Founding team
Robert grew up in Kazakhstan, studied computer science at KAIST in South Korea, and built his technical chops at two of the most demanding infrastructure environments outside of FAANG. At Palantir, he built a semantic search package that now runs across multiple internal AI teams. At Bloomberg, he scaled a market tick processing pipeline by 10x to handle 10 million ticks per second. Those are not toy problems: they're exactly the class of high-throughput, low-latency data pipeline challenges that Laminar's tracing infrastructure is built on. He's an active voice in the YC and developer tools community and posts regularly about agent debugging on LinkedIn.
Din also grew up in Kazakhstan and studied at KAIST, where he and Robert built their working relationship before co-founding Laminar. Before YC, he spent two years at Amazon building and scaling payment infrastructure at AWS, then a year at a drug discovery biotech in Korea building ML infrastructure. That combination is unusual: payments infrastructure demands near-zero error rates and high reliability; ML infrastructure for drug discovery demands working with probabilistic systems under scientific scrutiny. Both directly inform how Laminar approaches the hard problem of making non-deterministic AI agents debuggable and reliable. Din is active on LinkedIn and posts about agent tooling and open-source AI development.
What to show them
The core product is a high-throughput distributed tracing system. Sessions with thousands of spans per agent run, browser session recordings, real-time anomaly detection via Signals: this is not a typical SaaS backend. Laminar needs engineers who understand how to store, query, and stream observability data at scale. The press release names this explicitly as the priority use of the seed capital. Core skills: distributed systems, ClickHouse or similar columnar storage, gRPC/protobuf, Rust or Go, Python SDK development, OpenTelemetry, streaming pipelines Proof of work: Instrument an existing open-source agent (OpenHands or CrewAI work well) with Laminar's SDK, generate a real trace, then write a brief technical post identifying one bottleneck in the data pipeline from ingestion to query. Post it on GitHub or your blog before reaching out.
A cold email that works at Laminar
What Laminar screens for
The press release language is unusually direct: funds are earmarked for "scaling high-performance tracing infrastructure" and "growing the engineering team." For a 6-person company, that's not boilerplate, it's a headcount plan. The open-source distribution model (GitHub repo at lmnr-ai/lmnr, integrations into two of the most active open-source agent platforms) means their next critical hire is someone who can work in public, ship fast, and build community trust alongside product features. Ant Wilson's involvement as an angel matters here: he built Supabase's developer community from zero to one of the most active open-source ecosystems in infrastructure. His bet signals that Laminar is thinking about community-led growth as a core go-to-market motion, not just enterprise sales. Atlantic.vc, the lead investor, has a portfolio that skews toward developer infrastructure (Lasso Security, Fathom Analytics). Their typical playbook post-seed is to push portfolio companies toward enterprise sales readiness within 12 months, which means a GTM hire is likely before the Series A.
A tailored CV beats a generic one. Use Laminar's job description language to clear filters.
Don't make these mistakes
Sending a generic cold email about 'your passion for observability.' These founders are engineers first. They respond to people who have actually used the product, found something worth improving, and show the work. Complimenting the fundraise is noise. Opening with a proof-of-work contribution is signal.
Mistakes that kill Laminar applications
A recycled CV gets rejected fast at Laminar (<50 people). They notice.
Skip 'I'm looking for...' — start with The observability category was built for simple request-response LLM calls and your specific angle on solving it.
The wait-and-hope strategy fails. Follow up on day five — response rates roughly double.
Applying to Laminar? Get the contact, not the form.
The Laminar interview process
3 stages · 7 days typical · take-home: no · modelled from similar companies
We don't yet have verified candidate reports for Laminar. What follows is the typical process for a <50-person B2B, Engineering, Product and Design company — treat it as a model, not confirmed detail.
Interview stages
Intro Call
Video call · 30 min
Culture fit and role expectations
Founder or hiring manager
Technical Deep Dive
Video call or in-person · 60 min
Past projects and problem-solving approach
Technical founder or lead
Final Round
In-person or video · 45 min
Team fit and offer discussion
Founding team
Laminar interview timeline
Timeline: ~ days. That's faster than the B2B, Engineering, Product and Design median (10 days at <50 people).
Interviewed at Laminar?
Tell us how it went — stages, questions, timeline. Takes 90 seconds and it's how this page stays accurate for the next person.
Submit your Laminar interview experience →Laminar jobs, frequently asked questions
How many jobs does Laminar have open?
3 open roles at Laminar, last checked March 2026.
Does Laminar hire remotely?
No remote roles right now — all positions are in London.
What roles is Laminar hiring for?
Laminar is hiring across Engineering. The most recent opening is Backend / Infrastructure Engineer.
How do I apply for a job at Laminar?
Apply via the links above. For tips, read our guide on how to get hired at Laminar.
Does Laminar respond to cold emails?
Not enough data yet on Laminar's cold email response rates.
Who is the hiring manager at Laminar?
At this size, hiring is usually run by a founder or department head.
How competitive is it to get hired at Laminar?
Typical applicant count for B2B, Engineering, Product and Design roles (<50 people): 50-100 in two weeks. Apply fast.
How many rounds is the Laminar interview?
3 stages: Intro Call, Technical Deep Dive, Final Round.
Is the Laminar interview hard?
Focus on relevant experience and culture fit, not puzzles. Final Round is reportedly the most challenging round.
Does Laminar give a take-home task?
No, Laminar does not include a take-home stage.
How long does Laminar take to get back to you?
Around 7 days across the full process.
What should I prepare for the Laminar interview?
relevant experience and culture fit is the priority. Show you can work autonomously — that matters more than algorithms at <50 people.
Where is Laminar based?
Laminar is headquartered in London.
Get Laminar roles before they're posted
A role stays uncontested for about four days. Here's the window — and where we put you in it.
From $9/month, cancel any time.
Watching Laminar
0 applicantsRole spotted & verified
1You get the alert
1You've applied
~8Hits the job boards
250+