About the role
About Boson AI: At Boson AI, we are not just building AI solutions; we are pioneering the future of enterprise AI. Driven by a passion for cutting-edge AI research, particularly in the transformative areas of large language models and agentic systems, our mission is to tackle the most complex real-world problems for businesses and unlock significant value. We are a dynamic and collaborative team of researchers and engineers who thrive on pushing the boundaries of what's possible, dedicated to delivering high-quality, reliable products that seamlessly integrate into the fabric of enterprise workflows and set new industry standards.
About the Role: Help build and operate the core platform behind Boson's model APIs and agentic products. You'll work alongside senior engineers on the infrastructure that every Boson agent runs on — API serving, state management, data pipelines, context retrieval, and execution runtime — shipping real features while growing into deeper ownership over time. This is a role for someone early in their career who wants to learn distributed systems by building them, with strong mentorship and meaningful production responsibility from day one.
Responsibilities
- Contribute to the core platform infrastructure: the API serving layer, state management, policy enforcement, and execution runtime for agentic workflows — starting with well-scoped components and taking on broader ownership as you grow.
- Help build and maintain distributed services that back our model API products, including request routing, rate limiting, and multi-tenant isolation, under the guidance of senior engineers.
- Build and maintain pieces of our data pipelines (ETL/ELT) for API logs, usage analytics, and billing, with a focus on data correctness and freshness.
- Develop and improve internal SDKs and libraries — writing clean, well-tested code with clear contracts that product teams can rely on.
- Support our context and memory systems for conversational workloads: retrieval, caching, and integration with vector stores and retrieval pipelines.
- Add observability across the platform — structured logging, tracing, and metrics — and help investigate and resolve reliability issues.
- Collaborate with ML and product teams to integrate model serving, voice runtime, and tooling infrastructure, learning how the full stack fits together.
Qualifications
- 0–2 years of professional software engineering experience (internships, co-ops, and strong personal or open-source projects count), or a recent CS degree with equivalent hands-on work.
- Solid programming fundamentals and a genuine interest in backend and distributed systems — you understand concepts like concurrency and fault tolerance and are eager to apply them in production.
- Some exposure to building backend services, APIs, or data processing — through work, coursework, or projects.
- Proficiency in at least one language such as Python, Go, Java, Rust, or C++, and a willingness to pick up new ones.
- Familiarity with the basics of cloud infrastructure (AWS/GCP), containers (Docker/K8s), version control, and CI/CD — or clear enthusiasm to learn them quickly.
- Curiosity, strong communication, and a collaborative mindset — you ask good questions, welcome feedback, and want to grow.
Bonus points
- Coursework, projects, or internship experience touching LLM serving, retrieval, or agentic systems.
- Exposure to data pipeline tools (Kafka/Kinesis, Spark/Flink, Airflow) or agent frameworks.
- Experience with real-time media (audio/video streaming) or any latency-sensitive system.
- A track record of shipping something end-to-end — a side project, a hackathon build, or an open-source contribution you're proud of.