• Develop and maintain APIs using the FastAPI framework. • Implement background tasks and asynchronous processing to optimize system performance. • Designing and building LLM-powered features and pipelines (RAG, agents, tool use, multi-step reasoning chains) • Context engineering — structuring prompts, managing context windows, optimizing token usage, implementing retrieval strategies to feed LLMs the right information at the right time • Working with LLM APIs (Claude, OpenAI, etc.) and orchestration frameworks • Building evaluation and testing frameworks for LLM outputs (accuracy, hallucination detection, regression testing) • Implementing guardrails, content filtering, and responsible AI patterns • Optimizing latency and cost for LLM-heavy workloads (caching, streaming, batching) • Write clean, efficient, and maintainable code that adheres to industry best practices.

• Develop and maintain data pipelines and automated workflows for collecting and processing data • Design, manage and optimise structured datasets used across the organisation • Write scripts and services to extract, transform and load data from various sources • Support journalists, analysts and product teams with accessing and working with data • Ensure data quality, consistency and reliability across datasets • Identify opportunities to improve automation and efficiency in data workflows • Collaborate with internal stakeholders including developers, designers, UX specialists and product teams • Contribute to the development of new data products, tools and services

• Kalepa is looking for a Senior Applied AI Engineer with 5+ years of experience to lead the framing, development, and deployment at the scale of machine learning models. • As an Applied AI Engineer you will lead the framing, development, and deployment at scale of machine learning models to understand the risk of various classes of businesses. • You will be turning vast amounts of structured and unstructured data from many sources (web data, geolocation, satellite imaging, etc.) into novel insights about behavior and risk. • Team members are given full ownership over their projects and are expected to drive the project’s direction and maintain focus. • The team works in a two-week sprint, and AI Engineers will work closely with Product Management and Software Engineers.

• Architect and code sophisticated AI modules, including high-performance embedding pipelines, custom chunkers, and advanced retrieval evaluators • Lead the integration of intelligent agent services with diverse internal and external APIs and vector databases to solve complex, cross-service challenges • Stay at the bleeding edge of AI research, implementing the latest advancements in fine-tuning, RLHF, and prompt engineering frameworks like DSPy • Drive agile excellence by spearheading sprint deliveries and collaborating with cross-functional leaders to define the scope of transformative AI features • Champion code quality and team growth by performing high-level peer reviews and contributing to shared utility libraries that boost development velocity • Architect and implement modular, cloud-native microservices that integrate GenAI into our production ecosystem, ensuring our Agentic solutions are as scalable and reliable as they are intelligent • Take ownership of the production lifecycle by building robust CI/CD pipelines and using observability frameworks (like Datadog or Databricks) to monitor model health, trace agent logic, and ensure system uptime • Drive technical excellence by developing comprehensive evaluation suites—incorporating both traditional testing and modern LLM-based evals—to benchmark accuracy, safety, and performance before every release