About the role
We are looking for a Staff Applied AI Engineer to join Aviva Services Excellence Centre (ASEC) and help design and deliver production AI agents and applied AI systems that create measurable value across Aviva’s customer-facing and internal operations. This is a senior, hands-on engineering role for someone who can work independently across the applied AI stack—from context engineering and agent orchestration to evaluation, memory and multimodal interfaces. You will partner with product, business, architecture, platform, data, risk and compliance teams, while helping shape the reusable engineering patterns that define how AI is built at Aviva.
What will you be doing?
- Designing, building and operating production-grade AI agents, context pipelines and applied AI services.
- Making architecture decisions for individual AI systems, including framework selection, orchestration patterns and memory strategy.
- Defining evaluation criteria before development begins and implementing robust evaluation frameworks covering quality, safety, fairness and compliance.
- Turning business needs into practical AI solutions in close partnership with product and business teams.
- Making pragmatic build-versus-reuse decisions and contributing reusable components, standards and canonical engineering patterns.
- Writing clean, testable Python code and use AI-assisted engineering tools effectively.
- Maintaining production reliability, monitoring cloud and API resource usage, and supporting incident response for deployed AI systems.
- Identifying and escalating architectural, data, compliance and responsible AI risks.
- Providing technical guidance to less experienced engineers and contributing actively to architecture and design reviews.
In Aviva Services Excellence Centre, we provide:
- Contract of employment
- Performance Bonus
- Private medical care (ENEL-MED)
- Cafeteria system of benefits (e.g. MultiSport card)
- Additional parent privileges: baby leave – 6 weeks leave for second parent; shortened working time after parental leave
- Employer-funded group insurance
- Employee Shares Plan
- Extra day off for birthday
- Paid time off to volunteer
- Additional leave acquired over the years in the company (even 5 days more in a year)
- Wellbeing Leave - additional two weeks paid leave after 10 years of service
- Psychological support consultations
- Access to the e-learning platforms
- Internal employee referral program
- Hybrid working model from Poland with a few days in Warsaw office per month
- Attractive office location in Warsaw - Gdański Business Center
- Additional entitlements for people with disabilities - Work Without Barriers
- Work environment that promotes diversity - Diversity Charter
Must have:
- Strong Python engineering skills and a track record of writing clean, testable, production-quality code.
- Proven experience delivering large language model applications in production, such as AI agents or advanced context pipelines.
- Strong communication skills and the ability to work effectively with both technical and business stakeholders.
- A degree in computer science, engineering, mathematics or a related discipline, or equivalent practical experience.
- A demonstrable portfolio of production AI or large language model engineering work.
Preferably:
- Deep understanding of context engineering, including chunking, embedding selection, hybrid search, re-ranking, knowledge graphs and prompt construction.
- Hands-on experience with agent orchestration frameworks such as AWS Strands, OpenAI Agents SDK, Google ADK or DSPy, or with implementing agent loops directly through APIs.
- Practical experience building or consuming Model Context Protocol (MCP) servers.
- Experience implementing production evaluation frameworks using tools such as DeepEval, Arize Phoenix, Galileo or LangSmith.
- Understanding of session, long-term and semantic memory architectures, including frameworks such as Mem0.
- Experience with AWS and operating AI systems in production.
Great to have:
- Experience fine-tuning models using tools such as Unsloth, Axolotl or Hugging Face TRL.
- Experience with speech-to-text or text-to-speech models, such as ElevenLabs, Deepgram or Qwen, in end-to-end voice solutions.
- AWS certification, such as Solutions Architect Associate or higher.
- Experience in financial services, insurance or another regulated industry.
- Working knowledge of data protection and customer-outcome requirements as they apply to AI systems.
