Senior AI Engineer
Who we are:
Adaptiq is a technology hub specializing in building, scaling, and supporting R&D teams for high-end, fast-growing product companies in a wide range of industries.
About the Product:
We are developing an AI-first platform that brings together multiple maritime data sources into a single, unified operational view. The platform creates a digital twin of global maritime activity and uses behavioral analytics together with predictive AI models to identify risks such as smuggling, illegal fishing, container risk, and other compliance or security threats.
The system delivers mission-grade intelligence for both commercial and government stakeholders.
Operating at global scale, the platform processes millions of events and terabytes of geospatial data every day. It is built on cloud infrastructure and microservices, and is closely connected with research prototypes developed by data science teams.
About the Role:
You will become part of an autonomous team focused on building agentic AI capabilities within a production-grade maritime intelligence platform.
As a Senior AI Engineer, you will design, develop, and deploy production-ready AI systems based on LLMs, autonomous agents, and retrieval-augmented generation (RAG). You will be involved across the full AI application lifecycle - from experimentation and prompt engineering to scalable deployment, evaluation, monitoring, and continuous improvement.
You will work closely with platform engineers, researchers, and product teams to turn AI prototypes into reliable, secure, and scalable production systems.
Key Responsibilities:
- Design, build, and deploy production-grade AI applications using LLMs, RAG, and agentic workflows.
- Develop and optimize autonomous AI agents that can plan, use tools, make decisions, and handle complex operational tasks.
- Integrate foundation models and LLM APIs into scalable systems, including retrieval pipelines, vector search, prompt orchestration, and AI memory.
- Create AI evaluation and observability frameworks, including hallucination detection, trace analysis, model performance monitoring, experimentation, and continuous improvement.
- Build scalable Python backend services and connect AI capabilities with distributed production systems.
- Collaborate with research and product teams to productionize new AI capabilities and bring them from experimentation to reliable real-world usage.
- Own technical decisions and promote AI engineering best practices, including architecture, testing, tooling, deployment, and AI-SDLC standards.
Required Competence and Skills:
- 7+ years of software engineering experience, including at least 1.5 years of hands-on experience building production AI applications, with proven experience delivering agentic AI systems used by real users.
- Strong software engineering background in Python or another backend language such as Golang, Rust, TypeScript, Java, or similar, with willingness to work mainly with Python.
- Hands-on experience building agentic AI systems using frameworks such as LangChain, LangGraph, CrewAI, DeepAgents, OpenClaw, Hermes, or similar.
- Experience deploying and operating production AI services in cloud environments.
- Proven experience designing scalable, event-driven architectures using messaging systems such as SQS/SNS and SQL/NoSQL databases.
- AWS experience is preferred.
- Experience integrating AI agents and AI-powered capabilities into production applications through GraphQL or REST APIs.
- Experience taking AI applications from development to production and collaborating with platform engineering teams on deployment and operations using Kubernetes and Terraform.
- Experience ensuring production AI systems are reliable, secure, observable, and ready for mission-critical use, including monitoring and incident response.
- Excellent communication skills, autonomy, and accountability in ambiguous, fast-moving environments.
Nice to Have:
- Experience with React.js and full-stack development, with the ability to contribute to frontend development when needed.
- Experience with vector databases and similarity search in production AI applications.
Why Us:
We provide 20 days of vacation leave per calendar year, plus official national holidays of the country you are based in.
We provide full accounting and legal support in all countries we operate.
We utilize a fully remote work model with a powerful workstation and co-working space in case you need it.
We offer a highly competitive package with yearly performance and compensation reviews.