Staff Backend Engineer - AI Agents (Healthcare) at 100ms

About Us 100ms is building AI agents that automate complex patient access workflows in U.S. healthcare,  starting with benefits verification, prior authorization, and referral intake in specialty pharmacies. We help care teams reduce delays and administrative burden so that patients can start treatment faster. Our automation platform combines deep healthcare knowledge with LLM-based agents and robust ops infrastructure. You’ll be joining a specialised team at 100ms focused on healthcare automation using AI. The Role As a Staff Backend Engineer, you will be a technical leader responsible for shaping the architecture and reliability of the systems that power our AI-driven healthcare automation platform. You’ll work at the intersection of distributed systems, LLM orchestration, and healthcare data infrastructure, driving decisions that affect the entire engineering organisation. What You’ll Do • Define and evolve the backend architecture for our AI agent platform, ensuring scalability, reliability, and security across healthcare workflows. • Design and build high-throughput, fault-tolerant services using Python (Django/FastAPI) or Go that orchestrate LLM-based agents, handle complex state machines, and integrate with external healthcare systems. • Own the technical direction of critical backend systems — from API design and data modelling to infrastructure-as-code and deployment pipelines. • Lead the design of robust observability, monitoring, and alerting frameworks to maintain SLA guarantees in a regulated healthcare environment. • Drive cross-team technical alignment by writing RFCs, leading architecture reviews, and establishing engineering standards and best practices. • Mentor and uplift senior and mid-level engineers through code reviews, pairing sessions, and technical guidance. • Partner closely with product, data science, and ops teams to translate ambiguous business problems into well-scoped technical solutions. • Identify systemic risks, tech debt, and performance bottlenecks — and proactively drive resolution with long-term thinking. Who Can Apply • Bachelor’s or Master’s degree in Computer Science, Information Technology, or equivalent practical experience. • 8+ years of professional software engineering experience, with at least 2–3 years operating at a staff or principal level. • Deep expertise in Python (Django/FastAPI) or Go for building production-grade backend systems. • Strong track record of designing and scaling distributed systems, microservices, and event-driven architectures. • Proven ability to lead technical strategy across teams — writing RFCs, influencing architecture decisions, and setting engineering standards. • Advanced knowledge of data structures, algorithms, system design, and computer science fundamentals. • Experience designing RESTful and/or gRPC APIs with deep attention to observability, fault tolerance, and backward compatibility. • Comfortable navigating ambiguity and driving clarity in complex, cross-functional problem spaces. Good to Have • Experience building or integrating LLM-based systems, AI agents, or ML pipelines in production. • Familiarity with healthcare data standards (HL7, FHIR, EDI/X12) or experience in regulated industries. • Hands-on experience with Kubernetes, Docker, and cloud platforms (AWS, GCP, or Azure) at scale. • Experience with event streaming platforms (Kafka, Pub/Sub) and asynchronous processing patterns. • Track record of contributing to open-source projects or speaking at technical conferences. • Fluency in English with strong written and verbal communication skills. • A growth mindset and openness to giving and receiving constructive feedback. Why 100ms • You will be part of a small, high-impact team at a fast-growing engineering-first startup. • You will work with engineers across the globe with experience at places like Facebook and Hotstar. • You will shape the technical direction of a platform that directly improves patient outcomes in U.S. healthcare. • You can grow as a deep individual contributor or as a technical leader — freedom to set your own trajectory. • You will tackle hard problems at the intersection of AI, distributed systems, and healthcare infrastructure. Additional Information At 100ms, we place a strong emphasis on in-office presence to promote collaboration and strengthen company culture. Under the current policy, employees are expected to work from the office at least three days a week - Tuesday, Wednesday, and Friday. Website: www.100ms.ai