Job description:
We are looking for a driven AI Engineer to join our engineering team. In this role, you will focus on building, testing, and deploying autonomous AI agents and multi-agent systems. You will bridge the gap between traditional software engineering and modern Generative AI, working to enable LLMs (Large Language Models) to interact with external tools, APIs, and data sources.
What you ll do
Agent Development & Testing: Perform development activities focused on AI Agents, including designing prompt chains, implementing tool-calling logic (function calling), and conducting unit tests for stochastic AI outputs. Work on projects involving RAG (Retrieval-Augmented Generation) and contribution to agent frameworks.
Performance Optimization: Participate in the estimation process for AI features. Diagnose and resolve specific AI performance issues, such as latency in LLM responses, token usage optimization, and reducing hallucination rates in agentic workflows.
Documentation & Knowledge Sharing: Document agent architectures, prompt templates, and "chains of thought" so that other developers can understand and iterate on the AI logic with minimal effort.
Full-Stack AI Integration: Develop and operate scalable AI applications from the backend logic (Python/LangChain) to the API layer, focusing on security (Guardrails) and operational excellence. Ensure agents can reliably execute tasks in a production environment.
Modern AI Practices: Apply modern software and AI engineering practices, including LLMOps, evaluation pipelines (Evals), vector database management, and standard CI/CD/Infrastructure-as-code.
System Integration: Work across teams to integrate AI Agents with existing internal systems, Data Fabric, and third-party APIs to enable agents to perform "actions" rather than just generating text.
Innovation & Agile: Participate in technology roadmap discussions to turn business requirements into functional autonomous agent solutions. Collaborate within a tight-knit engineering team employing agile practices.
Debugging & Triage: Triage product issues related to unpredictable model behavior. Debug, track, and resolve issues by analyzing traces (e.g., LangSmith, Arize) to understand the root cause of agent failures or loop errors.
Implementation: Able to write, debug, and troubleshoot code in mainstream open-source AI technologies (specifically Python). Lead efforts for Sprint deliverables and solve problems of medium complexity regarding context management and memory.
What experience you need
Bachelor's degree or equivalent experience
2+ years of IT engineering experience
Languages: Proficiency in Python is mandatory. Experience with JAVA is a plus.
Frameworks: Familiarity with Agentic frameworks (e.g., ADK, LangChain, LangGraph).
GenAI Fundamentals: Understanding of how LLMs work, including Context Windows, Temperature, Embeddings, and Vector Stores (e.g., Pinecone, Milvus, Weaviate).
APIs: Experience building and consuming RESTful APIs (assistants interacting with software).
What could set you apart
Prompt Engineering & Optimization: Advanced techniques (Chain-of-Thought, ReAct, Tree of Thoughts).
Cognitive Architectures: Designing memory systems (short-term vs. long-term) for agents.
AI Evaluation: Building automated test suites to grade agent performance.
Systems Thinking: Understanding how non-deterministic AI components fit into deterministic software systems.
Agile Engineering Best Practices.
Never miss an opportunity! Create an alert based on the job you applied for.