About the Role
We are looking for an experienced, hands-on Senior AI Software Engineer to join our AI engineering team and contribute to the design, development, and deployment of production-grade AI systems.
The ideal candidate combines strong software engineering fundamentals with practical experience in Large Language Models (LLMs), Agentic AI, distributed systems, and Retrieval-Augmented Generation (RAG).
This role requires someone who can take ownership of complex technical challenges, make sound architectural decisions, and transform AI prototypes into reliable, scalable, and maintainable software solutions.
Key Responsibilities
- Design, develop, and optimize LLM-powered applications and agentic AI systems.
- Build intelligent AI agents capable of reasoning, planning, tool calling, and executing multi-step workflows.
- Design and implement advanced RAG pipelines, including document processing, indexing, retrieval, reranking, and answer generation.
- Develop and maintain reliable backend services and APIs using Python and Node.js.
- Design and implement event-driven architectures and distributed messaging systems using Apache Kafka and RabbitMQ.
- Build reliable asynchronous communication and processing pipelines with appropriate message delivery, retry, and failure-handling mechanisms.
- Design evaluation pipelines to measure retrieval accuracy, answer quality, faithfulness, hallucination, and overall system performance.
- Improve the reliability, scalability, latency, and resource efficiency of AI applications.
- Integrate LLMs with external tools, databases, APIs, and enterprise services.
- Implement monitoring, logging, tracing, and error-handling mechanisms for production AI systems.
- Collaborate with product managers, AI researchers, backend engineers, and infrastructure teams to deliver end-to-end solutions.
- Participate in technical architecture decisions, code reviews, troubleshooting, and mentoring other engineers.
Required Qualifications
- At least 5 years of professional software engineering experience, including hands-on experience developing AI/ML applications.
- Advanced proficiency in Python and Node.js, with strong knowledge of OOP, design patterns, asynchronous programming, and clean code principles.
- Proven experience building and deploying LLM-powered applications in production environments.
- Strong understanding of LLM architectures, prompt engineering, structured outputs, function calling, and agentic workflows.
- Practical experience with RAG architectures, including embeddings, semantic search, hybrid retrieval, reranking, and vector databases.
- Experience with vector databases and search technologies such as Qdrant, Milvus, FAISS, Elasticsearch, or OpenSearch.
- Strong backend development skills, including FastAPI, Fastify, RESTful APIs, and SQL/NoSQL databases.
- Strong hands-on expertise in Apache Kafka and RabbitMQ, including message producers and consumers, exchanges, queues, topics, consumer groups, message acknowledgment, retries, dead-letter queues, and fault-tolerant message processing.
- Solid understanding of event-driven architecture, asynchronous communication, and distributed messaging patterns.
- Experience with Docker, Linux, Git, and modern software development practices.
- Understanding of software architecture, distributed systems, scalability, reliability, and performance optimization.
- Experience designing tests and evaluation methodologies for AI applications.
- Strong analytical thinking, problem-solving abilities, and the ability to independently own technical deliverables.
Nice to Have
- Experience with multi-agent systems, agent orchestration, workflow management, and human-in-the-loop architectures.
- Familiarity with advanced retrieval techniques, including GraphRAG, knowledge graphs, and query decomposition.
- Experience with LLM inference and serving frameworks such as vLLM, SGLang, llama.cpp, Hugging Face Transformers, or Ollama.
- Experience with fine-tuning, LoRA/QLoRA, or model adaptation techniques.
- Familiarity with LLM observability and evaluation tools such as LangSmith, Langfuse, Ragas, or DeepEval.
- Experience deploying AI solutions in on-premises or private cloud environments.
What We Value
- Engineering ownership: Ability to take responsibility for technical solutions from initial design to production deployment.
- Practical problem-solving: A strong preference for measurable improvements and reliable implementations over unnecessary complexity.
- Technical judgment: Ability to evaluate architectural trade-offs and select appropriate technologies based on real requirements.
- Quality mindset: Commitment to clean, tested, maintainable, and well-documented code.
- Collaboration: Ability to communicate technical decisions clearly and work effectively across engineering and product teams.
- Continuous learning: Interest in emerging AI technologies and the ability to distinguish practical advances from hype.
What We Offer
- Opportunity to work on technically challenging, production-grade AI systems.
- Meaningful ownership over architecture and technical implementation.
- Collaboration with experienced AI, software engineering, and infrastructure teams.
- Opportunities to experiment with modern LLMs, AI agents, and emerging AI technologies.
- An engineering-driven environment focused on technical excellence, innovation, and continuous improvement.
How to Apply
Please submit your resume along with your GitHub profile or examples of relevant technical work, if available.
We are particularly interested in candidates who can demonstrate hands-on experience building, evaluating, and deploying real-world LLM, RAG, agentic AI, and distributed backend applications.