Senior Software Developer(Python)

Our client is a rapidly expanding AI-driven technology company that focuses on delivering scalable, enterprise-grade solutions. Specializing in AI systems, cloud architecture, and custom software development, they serve a diverse range of global clients. They are seeking a Senior Software Developer with strong expertise in Python to join their team in a hybrid or remote capacity. This role reports directly to the Founder or Engineering Head and requires 5 to 7 years of relevant experience.

Key Responsibilities

- Design end-to-end solutions, including architecture planning and post-deployment optimization.
- Lead engineering execution with a hands-on approach, working closely alongside architecture teams.
- Own DevOps processes, including CI/CD pipelines and deployment workflows.
- Drive performance improvements across the entire engineering stack.
- Develop and deliver real-world, user-facing AI and agentic applications.
- Take full product ownership, including managing partner-facing deliverables.
- Lead and mentor the engineering team to foster growth and collaboration.
- Design and implement multi-agent orchestration architectures, covering agent routing, task delegation, memory management, and inter-agent communication.
- Architect semantic layers such as knowledge graphs, vector stores, retrieval pipelines, and structured data abstractions for AI consumption.
- Clearly present and explain architectural decisions to both technical and non-technical stakeholders.

Required Qualifications

- Strong proficiency in Python as the primary programming language.
- Exceptional system design skills are essential.
- Hands-on experience with agentic AI frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or similar.
- Proven track record of building agentic AI applications from end to end.
- Expertise in multi-agent orchestration, including designing supervisor/worker agent hierarchies, tool-use patterns, and stateful workflows.
- Deep understanding of semantic layer architecture, including RAG pipelines, embedding strategies, vector databases (e.g., Pinecone, Weaviate, pgvector), and knowledge retrieval systems.
- Experience designing scalable GenAI systems powered by large language models (LLMs), including prompt pipelines, context management, model routing, and output validation.
- Familiarity with GenAI infrastructure considerations such as latency, cost, and reliability trade-offs across providers like OpenAI, Anthropic, Gemini, and open-source models.
- Proficiency in DevOps and CI/CD tools such as GitHub Actions, Docker, and Kubernetes or their equivalents.
- Experience with post-deployment monitoring, scaling, and optimization.
- Minimum of 5 years of professional experience, with a strong preference for candidates with 7+ years.
- Demonstrated success in shipping real-world, user-facing products rather than internal tools or prototypes.
- Proven leadership experience in managing and mentoring engineering teams.

Preferred Qualifications and Benefits

- Experience working with cloud platforms such as AWS, Google Cloud Platform, or Azure.
- Background in AI product development or experience within AI startups is highly desirable.

This role offers the opportunity to work at the forefront of AI technology, contributing to innovative products that impact global clients. The position supports flexible working arrangements, including hybrid and remote options, fostering a dynamic and inclusive work environment.