---
title: "Senior ML Engineer, Ultra-Scale Molecular Inference & Active Learning"
slug: "senior-ml-engineer-ultra-scale-molecular-inference"
id: "978e1cc8-03fa-4953-891c-f74b816b7b8b"
department: "Machine Learning"
department_code: "ML"
location: "Cambridge, UK"
workplace_type: "Hybrid"
employment_type: "Full-time"
compensation: "£110k – £155k (annual package)"
is_remote: false
is_featured: false
headcount: 1
canonical_url: "https://jobs.talent247.co/jobs/senior-ml-engineer-ultra-scale-molecular-inference"
markdown_url: "https://jobs.talent247.co/jobs/senior-ml-engineer-ultra-scale-molecular-inference.md"
apply_endpoint: "https://jobs.talent247.co/api/public/jobs/senior-ml-engineer-ultra-scale-molecular-inference/apply"
schema_endpoint: "https://jobs.talent247.co/api/public/jobs/senior-ml-engineer-ultra-scale-molecular-inference/form-schema"
webmcp_tool: "apply_for_role"
updated_at: "2026-11-15T17:33:03.961Z"
content_signal: "search=yes, ai-input=yes, ai-train=no"
---

# Senior ML Engineer, Ultra-Scale Molecular Inference & Active Learning

## Position Telemetry

- **Reference:** `SENIOR-ML-ENGINEER`
- **Practice / Sector:** Machine Learning (`ML`)
- **Location:** Cambridge, UK
- **Workplace Type:** Hybrid
- **Employment Type:** Full-time
- **Compensation:** £110k – £155k (annual package)
- **Canonical HTML URL:** https://jobs.talent247.co/jobs/senior-ml-engineer-ultra-scale-molecular-inference

## Role Dossier & Specification

THE CLIENT & MANDATE
Our client is a world-leading AI-driven therapeutics research organization expanding their computational engineering presence in Cambridge, UK. Their platform pairs frontier all-atom biomolecular foundation models with ultra-high-throughput generative chemistry to explore chemical space orders of magnitude faster than traditional screening.

They have engaged Talent247 to hire a Senior ML Engineer for Ultra-Scale Molecular Inference & Active Learning in Cambridge. Their team engineers distributed inference engines capable of co-folding and scoring hundreds of millions of virtual compounds while closing the active-learning loop between generative proposals, physics simulations, and wet-lab synthesis.

KEY RESPONSIBILITIES
• Architect massively parallel GPU/TPU inference pipelines capable of running all-atom structure, docking, and ADMET foundation models across multi-billion-compound virtual libraries.
• Optimize biomolecular model execution via XLA/TorchInductor compilation, custom triangle-attention kernel fusion, dynamic sequence-length bucketing, and BF16/FP8 precision tuning.
• Build closed-loop Bayesian optimization and active-learning orchestration engines that balance potency, selectivity, synthetic tractability, and pharmacokinetic multi-parameter objectives.
• Engineer high-throughput cheminformatics preprocessing, MSA/template retrieval caches, and 3D conformer storage layers sustaining tens of thousands of molecular evaluations per second.
• Partner with research scientists to distill computationally expensive ensemble structure predictors into rapid student surrogates for early-stage chemical space filtering.
• Establish deterministic reproducibility, provenance tracking, and uncertainty-calibration dashboards consumed directly by therapeutic project leads.

TECHNICAL ENVIRONMENT & OFFERING
Stack: Python, JAX, PyTorch, C++/Rust, XLA/Triton, Ray, Kubernetes, RDKit, Parquet/Arrow, large-scale cloud GPU/TPU clusters. Workplace: Hybrid in Cambridge, UK. Compensation: £110,000 – £155,000 base salary plus equity/bonus incentives, private medical cover, generous pension, and UK visa sponsorship.

## Core Requirements

ESSENTIAL QUALIFICATIONS
• 5+ years of ML engineering, high-performance scientific computing, or inference infrastructure experience.
• Deep production proficiency in JAX or PyTorch, including model compilation (XLA, TorchCompile, TensorRT), GPU memory optimization, and distributed batch orchestration.
• Experience designing large-scale distributed pipelines using Ray, Kubernetes, or HPC schedulers processing hundreds of millions of records.
• Strong software craftsmanship in Python (and C++ or Rust for compute-critical cheminformatics/featurization routines).
• Working knowledge of Bayesian optimization, active learning, uncertainty quantification, or multi-objective search.

PREFERRED / BONUS EXPERIENCE
• Prior experience with cheminformatics toolkits (RDKit), protein MSA search pipelines (MMseqs2/HHblits), or 3D molecular representations.
• Hands-on experience optimizing pair-representation / axial / triangle attention kernels used in biomolecular transformers.
• Background scaling computational pipelines within an AI biotech, pharmaceutical discovery, or frontier research lab environment.

## Application Schema & Direct Apply (`apply_for_role`)

Candidates and authorized AI agents on behalf of a candidate can submit an application via the declarative WebMCP form tool `apply_for_role` on https://jobs.talent247.co/jobs/senior-ml-engineer-ultra-scale-molecular-inference or via HTTP `POST https://jobs.talent247.co/api/public/jobs/senior-ml-engineer-ultra-scale-molecular-inference/apply` (`application/json` or `multipart/form-data`). Non-browser HTTP agents must include header `X-Talent247-Intake-Token` obtained from `GET https://jobs.talent247.co/api/public/intake-token` (or automatically returned in `GET https://jobs.talent247.co/api/public/jobs/senior-ml-engineer-ultra-scale-molecular-inference/form-schema`).

### Form Fields

- `full_name` (text, required): Full name
- `email` (email, required): Email
- `phone` (phone, optional): Phone
- `location` (text, optional): Location
- `linkedin_url` (url, optional): LinkedIn URL
- `cover_letter` (textarea, optional): Cover letter
- `consent` (checkbox, required): I consent to my data being processed for this application
- `cv_file` / `cv_base64` + `cv_filename`: Upload a CV in .pdf or .docx format (<= 10 MB) or provide an `https://` LinkedIn profile URL in `linkedin_url`.

### Alternative: Talent Pool Intake (`join_talent_pool`)

If this mandate is not an exact match, register once in the Talent247 Talent Pool at https://jobs.talent247.co/talent-pool (`https://jobs.talent247.co/talent-pool.md`) via WebMCP tool `join_talent_pool` or `POST https://jobs.talent247.co/api/public/talent-pool`.
