AI Engineer

Lightrun is the world’s first developer observability platform. Our revolutionary developer-first approach enables engineering teams to connect to their live applications to continuously identify and tackle critical issues without hotfixes, redeployments, or restarts. By eliminating the need to reproduce bugs locally or issue a new software version for adding new logs or metrics to troubleshoot production issues, Lightrun's customers consistently reduce their MTTR by up to 50-60% and significantly improve development productivity. Issues that used to take 1-2 weeks to mitigate now take our customers on average less than an hour to solve. Lightrun also introduces AI-driven autonomous debugging capabilities, transforming the software development lifecycle (SDLC) by automating root cause analysis and significantly reducing manual intervention. Lightrun empowers our customers' developers by eliminating the need for costly developer lifecycle operations like reproducing locally or issuing a new software version just for adding new logs or metrics. With customers varying from Fortune 500 (including F10 companies) to SMEs and SMBs across multiple verticals, Lightrun is growing rapidly.

Responsibilities:

• Take part in the design and development of AI-driven features for our Dev-Native Observability Platform.
• Collaborate with cross-functional teams to integrate AI solutions into existing systems.
• Contribute to the product roadmap by identifying AI opportunities and providing insights as a potential end user
• Stay updated with the latest AI trends and technologies to ensure our platform remains cutting-edge.

Requirements:

• At least 3 years experience in Python working with AI/ML frameworks
• At least 5 years of backend experience with at least one additional programming language (Java / C# / Node.js / C++)
• At least 3 years experience working with database solutions (RDBMS, NoSQL, Vector)
• Proven experience with writing efficient and useful LLM prompts
• Proven experience building LLM-based solutions and integrating them into products
• Strong system and architecture design skills, particularly in designing LLM based systems
• Experience or at least substantial knowledge of GenAI technologies such as agentic flows, RAG, model fine-tuning / distilling, prompt engineering, context graphs, context awareness
• Hands-on experience with cloud platforms and their AI/LLM services
• Experience working in a startup environment, with the ability to adapt to fast-paced changes
• Self-driven, fast-paced learner
• A can-do and fearless attitude
• Team player, collaborative and high communication skills
• Experience working on a SaaS product - Advantage
• Experience working with customers and direct customers feedback - Advantage
• Experience using observability / profiling / remote debugging tools - Advantage