Agentic AI Engineer

About Apheris
We enable leading pharmaceutical teams to discover and develop drugs faster. We host the industry’s largest federated data networks for drug discovery AI, spanning co-folding, ADMET, and antibody developability.

Across these networks, models are trained on proprietary industry datasets to achieve higher performance and broader applicability while keeping data control and IP protected. We deliver these superior models through drug discovery applications that enable teams to run them at scale, further customize them, and integrate them into existing R&D workflows.

• AI Structural Biology (AISB) Network: Nine top-20 pharma companies collaborate in the field of co-folding, structure-based binding affinity predictions and antibody design.
• ADMET Network: Five top-50 pharma and biotechs collaborate to improve small-molecule property prediction and expand to further drug modalities.
• Antibody Developability Network: Pharma partners collaborate to federate historical and purpose-built antibody developability datasets for secure ML training, without data leaving each partner’s environment.

]]> About the role
This role is focused on building Apheris’ internal AI-first data foundation and deploying agentic workflows that materially improve how teams access information, make decisions, and execute. You will connect fragmented internal and external data sources and turn them into usable systems, enabling LLM-powered querying, automation, and decision support across the organization.

Your initial focus will be on commercial and cross-functional enablement, building systems that integrate meeting transcripts, email, Slack, CRM context, product documentation, and relevant external signals. On top of this foundation, you will design and deploy agentic workflows that are used securely in daily operations, not just prototypes.

This is a hands-on builder role with a high bar for output quality, speed, and ownership. The emphasis is on identifying high-leverage opportunities, shipping quickly, and turning working prototypes into reliable internal systems that create sustained impact. You will largely work with business stakeholders and have great visibility with leadership.]]> What you will do

Build Apheris’ AI-first internal data foundation

• Create a unified data layer across:
  • Meeting transcripts
  • Email and Slack communication
  • CRM and account context
  • Confluence
  • Product documentation
  • Selected external signals
• Design pragmatic data pipelines, schemas, and retrieval systems optimized for LLM access
• Ensure information is structured, queryable, and reliable for downstream workflows

Build agentic workflows and internal AI systems

• Design and deploy agentic workflows and LLM interfaces used daily by teams
• Deliver concrete, high-impact use cases such as:
  • Pre-meeting briefings with account context and recommended actions
  • Automated debriefs and follow-ups
  • Extraction of customer feedback into structured product insights
  • Cross-functional visibility into discussions and decisions
  • Translation of customer signals into product inputs
  • Competitive intelligence and internal knowledge synthesis
  • High-quality draft generation for internal and external communication
  • Marketing copy
  • Decision dashboards for senior leadership
• Continuously iterate based on real usage and feedback

Drive adoption and workflow transformation

• Identify high-value workflows across commercial, product, and leadership teams
• Replace manual, fragmented processes with AI-native workflows
• Shape how teams use AI in day-to-day work through tooling, interfaces, and patterns
• Focus on systems that are actually used, not just technically impressive

Turn prototypes into production-ready systems

• Move fast from prototype to reliable internal tooling
• Establish lightweight standards for:
  • Data quality and consistency
  • Access control and permissions
  • Monitoring and maintenance
• Balance speed with robustness to ensure sustained usage

Build secure, reliable, and non-destructive agent systems

• Enforce process isolation and strict permissioning to prevent unintended or destructive actions
• Ensure predictable, auditable behavior through clear execution boundaries, logging, and reproducibility
• Implement fail-safes, rollback mechanisms, and continuous testing to harden systems against errors and unsafe behavior

Contribute to company-wide AI-first transformation

• Act as a key driver in making Apheris an AI-native organization
• Bring in best practices from agentic AI, LLM tooling, and workflow automation
• Selectively contribute to adjacent technical systems where relevant

]]> What we expect from you

2–4 years of experience in applied AI, data systems, or building internal agentic tools in high-performance environments

Strong hands-on experience with:

• LLMs and retrieval-augmented systems
• Agent frameworks and orchestration
• Workflow automation across multiple systems
• Setting up secure execution environments (e.g., automated spawning of isolated, security-hardened runtimes for non-destructive agent operations)

Solid data engineering capabilities, including:

• Designing and maintaining data pipelines (batch and real-time)
• Building and managing structured data layers (e.g., event stores, data warehouses, vector databases)
• Integrating and normalizing data across heterogeneous sources (CRM, Slack, email, docs, product systems)
• Ensuring data quality, observability, and reliability for downstream AI systems

Exceptional execution bias and entrepreneurial drive

Experience building agentic workflows in real-world environments (not just experiments) – in particular, experience with integrating various data sources

Familiarity with tools such as Claude Code, Pi (OpenClaw), or similar agent systems

Experience integrating across communication tools, documentation systems, and internal platforms

Strong engineering and product judgment, plus a high bar for quality, speed, and ownership

Flexibility to jump across topics and work with various internal teams

Fluent English; German optional

]]> Nice to have

Background in fast-moving startup environments with high expectations on output

Exposure to scientific, technical, or data-intensive domains

]]> What we offer you

Industry-competitive compensation, including early-stage virtual share options

Remote-first working – work where you work best

Wellbeing budget, mental health support, work-from-home budget, co-working stipend, and learning budget

Generous holiday allowance

Office Days at our Berlin HQ or a different European location (3x per year)

A high-caliber, execution-focused team with experience from leading organizations

Significant ownership from day one and direct impact on how the company operates

The opportunity to shape how a fast-growing company becomes AI-first in practice

]]>