Key skills
CloudDockerFlaskGraphQLKafkaNoSQLOpen SourcePythonScikit-LearnSparkSQLAIMachine LearningMLGenAILLMOpenAIAnthropicRAGAgenticscikit-learnXGBoostLangGraphData EngineeringSnowflakeDatabricksFastAPIGitHubA/B Testing
About this role
Role Overview
- Assist with designing and optimizing prompts for LLMs across relevant use cases
- Help implement context management strategies (e.g., session memory, retrieval-augmented generation)
- Support integration and testing of LLMs within Python-based applications using APIs and standard data pipelines
- Participate in building, testing, and maintaining conversational and agent workflows (e.g., with LangGraph)
- Help maintain backend services, APIs, and data pipelines to ensure reliability and performance
- Work with product, data science, and engineering teams to gather requirements, test ideas, and iterate on solutions as part of a broader team
- Contribute to quality assurance efforts: testing, basic monitoring, and evaluation of prompt and workflow effectiveness
- Apply best practices in code quality, secure/ethical software development, and documentation by learning from peers and seeking feedback
- Support the implementation of data models and data pipelines, helping ensure data quality and integrity following established procedures
- Participate in technology evaluations and implementations for scalable and cost-effective solutions under senior supervision.
Requirements
- Experience with Python development (FastAPI, Flask; SQL/NoSQL databases)
- Experience with prompt engineering for LLMs (e.g., OpenAI, Anthropic, open source)
- Good understanding of context management concepts (session management, vector search, retrieval)
- Hands-on experience with agentic/conversational flow frameworks such as LangGraph
- Experience with Retrieval-Augmented Generation (RAG) and multi-agent workflow concepts
- Familiarity with cloud environments and basic containerization (Docker) is a plus
- Willingness to learn and apply modern API development and microservice patterns (REST, GraphQL)
- Exposure to data engineering tools/technologies (e.g., Spark, Kafka, Databricks, Snowflake) and SQL/another relevant language a plus
- Experience with AI-powered IDEs and tools (e.g., Visual Studio, GitHub Copilot, Windsurf, Cursor)
- Interest in, or basic exposure to, fine-tuning language models is a PLUS
- Interest in developing knowledge of statistics, machine learning (probability, hypothesis testing, experimentation, regularization), and their practical applications in business/AI contexts
- Experience supporting or learning about predictive model building and validation (e.g., feature engineering, model training, error analysis) using tools like scikit-learn or XGBoost/other ML libraries
- Willingness to assist with experiments and contribute to evaluation (offline metrics, basic A/B testing, quality monitoring) under senior guidance
- Awareness or interest in LLM evaluation strategies (including automated/human-in-the-loop, task quality, safety metrics)
- Some understanding or curiosity about RAG-focused data science, prompt optimization, and LLM troubleshooting
- Desire to develop hands-on skills with prompt optimization, adaptation techniques (LoRA/QLoRA, DPO/IPO), data labeling, and evaluation approaches
- Familiarity with basic system performance considerations for LLMs (token optimization, latency, model routing) is a plus
- Openness to learning about interpretability and debugging practices for GenAI/AI systems.
Tech Stack
- Cloud
- Docker
- Flask
- GraphQL
- Kafka
- NoSQL
- Open Source
- Python
- Scikit-Learn
- Spark
- SQL
Benefits
- Competitive salary plus an annual company performance bonus
- Wellness & leisure time contribution
- Sickness compensation plan
- Premium medical services
- Family friendly benefits
- Meal contribution
- Extra days of vacation
- And much more