AI Engineer, Verisian
+ Employee Stock Options Plan
More information about location
Accelerating drug time-to-market
Be an early applicant
Accelerating drug time-to-market
1-20 employees
Be an early applicant
+ Employee Stock Options Plan
More information about location
1-20 employees
Company mission
To empower researchers and regulators to analyse and monitor studies transparently in real-time, leading to improved and safer therapies for devastating diseases.
Role
Who you are
- Experience with and foundational understanding of LLMs (especially open source models), including production deployment
- Experience with and foundational understanding of non-LLM AI, including production deployment
- Experience with RAG systems (Pinecone or similar)
- Strong interest in programming languages, parsing algorithms, interpreters, and compilers
- Extensive experience in Python, Pandas, and at least one other programming language
- Experience with and clear understanding of graph theory and algorithm implementation
- Highly motivated and highly independent, able to create and manage a code base
- We & mission mindset
- Iteration mindset
- Strong focus on building as a team
- Strong communication skills
- “If it’s not code and documented, it doesn’t exist”-mindset
Desirable
- Experience with code generation
What the job involves
- As an AI Engineer, you will join our world-class engineering team in building the Verisian Platform
- You will use the latest in AI, LLMs, and RAG systems and combine them with code and data traceability, the core of Verisian’s technology, to create the most reliable and accurate code generator to analyze clinical trials
- You will be expected to lead the analysis, design, engineering of the AI stack, including its RAG system, selection and fine-tuning of models, as well as its production-ready deployment
- As part of our core team, you will join us in designing, prioritising, building and testing new functionality, troubleshooting customer issues, finding root causes, and developing improvements to ensure maximal user impact and performance
- Our RAG system is based on Python and Pinecone and we have deployed a set of open source models
- We interact with our code and data traceability graph through our main application stack which is currently based on Next.js and deployed via Docker/Kubernetes in the cloud
- Our code analysis pipelines are based on Antlr4 and Java
- Git is where our code lives, and Github Actions is how it gets out into the world
- Your role will be to build the Verisian Agentic AI Scientific Computing Environment (SCE)
- It will resolve issues identified in our Validator, modify existing code, and create analyses from pre-existing templates and eventually from scratch
- It does so by checking out code using git, modifying it using our full study traceability insights (specifications, metadata, data, and code traceability), feeding its results back into the Verisian Platform, and ultimately reaching its goals through iterations guided by expert-reviews using the Verisian Validator
- The Agentic AI SCE will increase the speed with which clinical trials are analyzed and become a crucial part of the Verisian Builder
- In combination with the Verisian Validator that extracts full dataset and column-level data lineages and dependencies from existing clinical trials, the Verisian Platform will allow for the efficient creation, validation, understanding, modification, communication of clinical trials and enable code and data reuse
- Clinical trials will be analyzed and validated faster, better, and at lower costs to the benefit of all of humanity
Salary benchmarks
Our take
Drug development times are painfully long, with patients waiting years upon years for new medicines to hit the market. Verisian is hoping to change this, with a range of tools to facilitate faster drug trialling and analysis of results.
The company's products target know pain-points in the clinical trial pipeline. For example, Verisian Builder allows trials to be designed faster by supplying a library of pre-approved modules based on existing studies. Trials can be pooled for analysis with Verisian Pooler, while data can be extracted and virtualized with Verisian Tracer.
Through this suite of offerings, Verisian hopes to streamline clinical trials while maintaining their integrity, speeding up the time-to-market for new drugs. Fresh funding will be used to grow its engineering team as it creates the first version of its "Builder" product, as well as establish and grow its initial design partnerships with tier-1 pharmaceuticals.
Kirsty
Company Specialist at Welcome to the Jungle
Company
Funding (1 round)
Sep 2023
$1.4m
SEED
Total funding: $1.4m
Company benefits
- Build something that impacts the lives of people around the world
- Highly collaborative, ambitious and world-class team
- Employee Stock Options Plan
- All remote, asynchronous work environment
- Additional benefits depending on country of residence
Company HQ
Westminster, London, UK
Leadership
Tomás Sabat
(CEO)Was on the Founding Team at Vaticle, where they spent 6 years as COO. Obtained an MPhil from the University of Cambridge.
Henning Kuich
(CTO)Earned a PhD in Systems Biology from Freie Universität Berlin. Spent 7 years at Bayer Pharmaceuticals, ultimately as Senior Computational Scientist.
Share this job