Software Engineer

Software EngineerCompany is helping an on-demand, autonomous ride-hailing company find a Software Engineer to design and build production-grade AI applications, agents, and conversational systems. In this role, you'll develop AI-powered products that support complex task execution, decision-making, and customer interactions. You'll evaluate and integrate large language models, build Retrieval-Augmented Generation systems, and partner with cross-functional teams to deliver scalable, reliable AI solutions. The ideal candidate is an experienced software engineer with a strong Python and machine learning background, hands-on experience building AI applications, and a practical understanding of how to balance model accuracy, latency, cost, and user experience.As a Software Engineer, you'll:Design and develop AI agents and autonomous systems capable of complex task execution and decision-making.Build conversational AI applications, including chatbots and voice-based customer service systems.Develop AI-powered integrations across applications, platforms, and services.Design and optimize Retrieval-Augmented Generation systems using vector databases, embeddings, retrieval strategies, and prompt engineering.Develop, implement, and optimize machine learning models using PyTorch.Evaluate and select large language models based on accuracy, latency, cost, capabilities, and user experience.Translate business requirements into scalable technical AI solutions in partnership with cross-functional teams.Architect, deploy, and maintain production-grade AI systems with a focus on reliability, scalability, security, and performance.Monitor AI system performance and improve model quality, response accuracy, and operational efficiency.Ideal candidate profileBonus Qualifications: Proficiency in Kotlin programming Full-stack development experience with both backend and frontend technologies Cloud software development experience, especially microservices architecture and integration Experience with REST APIs, gRPC, and/or Kafka for service communication and event-driven architectures Knowledge of cloud platforms (AWS, GCP, Azure) for AI deployment Familiarity with containerization and orchestration (Docker, Kubernetes) Experience with AI frameworks like LangChain, LlamaIndex, AutoGen, or similar tools Understanding of CI/CD pipelines and DevOps practicesDaily tasksCore Responsibilities Design and develop AI agents and autonomous systems capable of complex task execution and decision-making Build conversational AI solutions including chatbots and voice-based customer service systems Create AI-powered application integrations across platforms and services Develop and optimize Retrieval-Augmented Generation (RAG) systems for enhanced AI application performance Implement and optimize machine learning models using PyTorch Evaluate and deploy appropriate LLMs based on specific needs—balancing accuracy, latency, cost, and user experience Collaborate with cross-functional teams to translate business requirements into technical AI solutions Architect and maintain production-grade AI solutions with focus on scalability, reliability, and performanceRequired skillsQualifications: 6+ years Proficiency in Python for AI/ML development 6+ years Experience with PyTorch (or willingness to learn for entry-level candidates) Understanding of AI agents and their application to real-world problems Hands-on experience or strong interest in building chatbots and/or voice-based conversational systems Knowledge of RAG system components: vector databases, embeddings, retrieval strategies, and prompt engineering Familiarity with major LLM providers (OpenAI, Anthropic, Google, Meta, etc.) and understanding of their trade-offs in terms of performance, cost, latency, and capabilities Understanding of transformer neural network architecture and attention mechanisms 6+ years Experience integrating AI capabilities into applications or eagerness to learn application developmentBusiness driver of roleQualifications: 6+ years Proficiency in Python for AI/ML development 6+ years Experience with PyTorch (or willingness to learn for entry-level candidates) Understanding of AI agents and their application to real-world problems Hands-on experience or strong interest in building chatbots and/or voice-based conversational systems Knowledge of RAG system components: vector databases, embeddings, retrieval strategies, and prompt engineering Familiarity with major LLM providers (OpenAI, Anthropic, Google, Meta, etc.