Senior AI Engineer

About the project: Intelligent systems that combine cutting-edge AI with robust backend architecture to revolutionize healthcare, redefine work-life balance, transform education, and elevate customer experiences.

• 8+ years of backend engineering experience with Django, Kafka, and PostgreSQL


• 4+ years of hands-on experience building and deploying machine learning systems


• Proven track record of implementing production RAG systems at scale 


• Strong experience in product management, including work estimation and roadmap planning


• Experience building solutions at scale with large enterprise data in healthcare, finance, or banking sectors


• Demonstrated ability to lead technical initiatives and architectural decisions


• Experience managing technical product roadmaps and providing accurate work estimations


• Strong problem-solving skills and ability to work independently on complex projects


• Strategic thinking ability to balance immediate solutions with long-term scalability


• Excellent collaboration skills when working with cross-functional teams


• Excellent written and verbal communication skills in English


• Driven, self-motivated, adaptable, empathetic, energetic, and detail-oriented

• Expert-level Python development skills with Django experience


• Deep understanding of distributed systems and message queuing using message broker systems (e.g., Kafka)


• Advanced PostgreSQL knowledge, including optimization for AI workloads


• Experience building and optimizing retrieval-augmented generation (RAG) systems


• Experience architecting and implementing multi-agent AI systems


• Knowledge of deep learning frameworks (PyTorch or TensorFlow) and NLP, particularly transformer architectures


• Experience with cloud platforms (AWS preferred) and containerization (Docker, Kubernetes)


• Experience building solutions using pre-trained LLMs (OpenAI, Claude, Llama, etc.)


• Strong background in MLOps practices and tools, including platforms like Langfuse or LiteLLM


• Proficiency in writing clean, well-documented code and troubleshooting complex issues


• Experience in testing and validating products and communicating results with stakeholders

• Experience applying graph algorithms to machine learning problems


• Strong experience with modern NLP techniques and transformer architectures


• Knowledge of evaluation metrics for NLP system performance


• Solid foundation in probability theory and statistical inference


• Experience with statistical modeling and hypothesis testing


• Understanding of sampling methods and experimental design

• Proven experience designing and implementing scalable LLM-powered systems in production environments


• Deep understanding of LLM orchestration and optimization techniques for high-throughput applications


• Experience with prompt engineering, fine-tuning, and context window management for optimal LLM performance


• Demonstrated expertise in LLM fine-tuning methodologies, including RLHF, PEFT, and LoRA techniques


• Experience building data collection pipelines for LLM training and fine-tuning


• Knowledge of efficient usage strategies, cost optimization for LLM API consumption, and performance optimization of large-scale deployments.


• Experience implementing LLM caching mechanisms and vector store optimizations


• Expertise in designing fault-tolerant LLM architectures with appropriate fallback mechanisms


• Understanding of techniques to reduce latency in LLM-powered applications


• Knowledge of strategies for handling data privacy and security in LLM applications

• Lead the design and implementation of production-ready RAG systems that integrate seamlessly with our backend infrastructure using Django, Kafka, PostgreSQL, and Clickhouse


• Architect multi-agent AI systems that operate effectively within our platform's constraints and understand business value implications.


• Drive product strategy by providing accurate work estimations and technical roadmaps with minimal supervision.


• Design and implement sophisticated vector search solutions, including graph-based RAG systems


• Architect and build highly scalable LLM-powered systems that can handle enterprise-level workloads


• Lead LLM fine-tuning initiatives to customize models for specific business domains and use cases


• Design and implement user feedback systems to collect, analyze, and incorporate insights for continuous improvement


• Optimize LLM performance, cost, and reliability in production environments


• Establish MLOps best practices using platforms like Langfuse or LiteLLM to ensure robust model monitoring and evaluation


• Mentor and develop junior engineers in AI/ML best practices


• Collaborate with cross-functional teams to translate business requirements into technical solutions


• Lead system architecture decisions and technical direction for AI initiatives


• Evaluate emerging AI technologies for potential adoption