Design and run protein evolution or RNA screening campaigns, develop cellular assays, analyze experimental data, and improve reproducibility.
Build and train biological sequence models, prepare experimental datasets, evaluate model performance, and validate model-generated designs with scientists.
Develop software and integrations for laboratory workflows, connecting experimental plans, protocols, video, annotations, and assay results.
Integrate AI assistants with laboratory software and instruments; evaluate laboratory action recognition and procedural error detection.
Summarised from the posting by AI and can be wrong. The full description is the source.
Requirements
Experience
Depth in at least one of protein and RNA engineering, machine learning and model training, or AI laboratory systems and automation
Evidence of completing substantial hands-on work, such as a validated assay, research project, model, or deployed system
Protein and RNA engineering: hands-on experience in molecular biology and mammalian cell culture, with demonstrated ability to develop and troubleshoot assays
Protein and RNA engineering: experience in at least one of protein engineering, directed evolution, CRISPR technologies, RNA biology, or pooled functional screening
Protein and RNA engineering: familiarity with quantitative experimental analysis
Machine learning and model training: practical understanding of transformer architectures, optimization methods, loss functions, and training dynamics, including diagnosing unstable training and overf
Machine learning and model training: experience building reproducible training pipelines and running GPU-based experiments, with systematic experiment tracking and model evaluation
Machine learning and model training: ownership of a substantial model training project, from dataset preparation through evaluation, in research or production
AI laboratory systems and automation: experience building systems used in real workflows, with attention to logging, traceability, and failure handling
AI laboratory systems and automation: experience in at least one of laboratory automation, instrument integration, AI agents, computer vision, or multimodal systems
Protein and RNA engineering: experience with primary human cells, sequencing library preparation, or high-throughput assays (preferred)
Machine learning and model training: experience with distributed training, biological foundation models, sequence generation, or learning from experimental feedback (preferred)
AI laboratory systems and automation: familiarity with wet-lab workflows (preferred)
Education
Master's degree in a relevant scientific or engineering field, or equivalent practical experience
Skills
Machine learning and model training: strong Python skills and hands-on experience implementing and training deep learning models in PyTorch, JAX, or a comparable framework
AI laboratory systems and automation: strong software engineering skills, including Python, APIs, data pipelines, testing, and debugging
Other requirements
Availability to work on-site five days per week
Ability to define milestones, investigate unexpected results, and communicate technical decisions clearly
Your match
Sign in and add your resume to see which of this job's requirements it shows.
Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.
Benefits
Health insurance
Health care plan
Dental & vision
Medical, dental, and vision coverage
Retirement plan
Retirement plan (401k, IRA)
Paid time off
Paid time off for vacation, sick leave, and public holidays
Equity
Stock option plan
Life & disability insurance
Life insurance (Basic, Voluntary & AD&D)
Full job description
From Acelegen’s careers site
Member of Technical Staff - Biological Engineering, ML, or Lab System
About the role
Acelegen combines biology, AI, and laboratory automation to accelerate scientific discovery and drug development. Our platform connects protein evolution in living human cells, RNA sequence-to-function mapping, and AI-assisted laboratory workflows.
We are seeking hands-on scientists and engineers to develop this platform and advance our discovery programs. You will own a defined technical problem from initial design through implementation, validation, and iteration. Depending on your background, your work will focus on one of the following areas.
Show full descriptionShow less
Candidates should bring depth in at least one of the following areas and be comfortable collaborating across disciplines.
1. Member of Technical Staff — Protein & RNA Engineering
Develop experimental systems that measure and improve how proteins and RNA function in human cells.
Responsibilities:
Design and execute protein evolution or RNA screening campaigns, defining functional objectives, experimental controls, and criteria for selecting promising variants.
Develop and optimize cellular assays that measure outcomes such as protein expression, binding, signaling, or cell fitness.
Generate and interpret sequencing, flow cytometry, or reporter assay data to connect sequence changes with biological function.
Investigate variability and failed experiments, improve reproducibility, and document protocols that other researchers can reliably execute.
Collaborate with computational scientists to select designs for testing and turn experimental results into datasets for model development.Relevant qualifications:
Hands-on experience in molecular biology and mammalian cell culture, with demonstrated ability to develop and troubleshoot assays.
Experience in at least one relevant area: protein engineering, directed evolution, CRISPR technologies, RNA biology, or pooled functional screening.
Familiarity with quantitative experimental analysis. Experience with primary human cells, sequencing library preparation, or high-throughput assays is a plus.
2. Member of Technical Staff — Machine Learning & Model Training
Train and improve protein and RNA models using Acelegen’s experimental data. You will own model development from training data preparation and objective design through large-scale training, evaluation, and experimental validation.
Responsibilities:
Develop training pipelines for pretraining, continued pretraining, and fine-tuning biological sequence models.
Design training objectives that connect protein and RNA sequences to experimentally measured function, including the effects of interacting mutations and cellular context.
Build training datasets from experimental screens, with rigorous filtering, normalization, versioning, and train–validation–test splits.
Run systematic experiments across model architectures, training objectives, data mixtures, and hyperparameters; use ablations to identify what drives improvements.
Optimize training efficiency and stability through distributed training, mixed precision, memory optimization, profiling, and reliable checkpointing.
Evaluate models on unseen sequences and experimental conditions, and work with scientists to validate model-generated designs and incorporate new measurements into subsequent training rounds.Relevant qualifications:
Strong Python skills and hands-on experience implementing and training deep learning models in PyTorch, JAX, or a comparable framework.
Practical understanding of transformer architectures, optimization methods, loss functions, and training dynamics, including diagnosing unstable training and overfitting.
Experience building reproducible training pipelines and running GPU-based experiments, with systematic experiment tracking and model evaluation.
Demonstrated ownership of a substantial model training project, from dataset preparation through evaluation, in research or production.
Experience with distributed training, biological foundation models, sequence generation, or learning from experimental feedback is a plus.
3. Member of Technical Staff — AI Laboratory Systems & Automation
Build software and integrations that connect experimental planning, laboratory execution, and structured feedback.
Responsibilities:
Develop tools that translate experimental plans into traceable workflows and capture their execution.
Build pipelines that connect protocols, video, timestamps, annotations, and assay results.
Integrate AI assistants with laboratory software and instruments to support researchers during experiments.
Develop evaluations for recognizing laboratory actions, detecting procedural errors, and assessing whether recorded evidence supports an experimental conclusion.
Debug systems in the laboratory and improve their reliability, usability, and recovery from failures.Relevant qualifications:
Strong software engineering skills, including Python, APIs, data pipelines, testing, and debugging.
Experience building systems used in real workflows, with attention to logging, traceability, and failure handling.
Experience in at least one relevant area: laboratory automation, instrument integration, AI agents, computer vision, or multimodal systems. Familiarity with wet-lab workflows is a plus.
Requirements
A Master's degree in a relevant scientific or engineering field, or equivalent practical experience.
Evidence of completing substantial hands-on work, such as a validated assay, research project, model, or deployed system.
Ability to define milestones, investigate unexpected results, and communicate technical decisions clearly.
Careful documentation and a collaborative approach to working across biology and engineering.