15 days ago
Bengaluru, IndiaStaff+
Responsibilities
- Own the end-to-end architecture of the AI agents platform, including services, APIs, data models, task pipelines, agent orchestration, and payer, EMR, and telephony integrations.
- Design reliability, latency, safety, fault-tolerance, idempotency, retry, observability, and graceful-degradation patterns for production agent workflows.
- Define architecture for multi-tenancy, data isolation, PHI handling, and HIPAA and SOC 2 requirements.
- Make and document build-versus-buy, service-boundary, storage, queueing, LLM-provider, and inference decisions.
- Prototype critical paths, write production code, and resolve ambiguous or high-risk technical problems.
- Partner with the platform team on Kubernetes infrastructure, autoscaling, deployment topology, cost, and SLOs.
- Mentor senior engineers and establish standards for testing, evaluation, design reviews, and release safety.
- Translate product and customer needs into an architectural roadmap and prepare the platform for scale.
Requirements
- 10+ years of professional software engineering experience, including several years designing and operating large-scale production distributed systems.
- Demonstrated ownership of product or platform architecture and foundational technical decisions.
- Deep backend expertise in service design, APIs, event-driven architectures, task queues, and relational and non-relational data modeling.
- Strong reliability-engineering knowledge, including observability, fault tolerance, capacity planning, and incident-informed design.
- Hands-on proficiency in Python or Go and ability to read and review React-based frontend code.
- Working knowledge of GCP, AWS or Azure, Kubernetes, infrastructure-as-code, and operational architecture.
- Experience building or integrating AI/LLM-backed systems, or evidence of quickly developing expertise in agent orchestration, evaluation, guardrails, and inference trade-offs.
- Strong security instincts involving data isolation, encryption, access control, and auditability.
- Excellent written and verbal communication and ability to drive complex, ambiguous technical problems to decisions.
- Preferred qualifications include voice AI, SIP, WebRTC, real-time systems, healthcare or regulated-domain experience, HIPAA, SOC 2, HITRUST, EMRs, payer integrations, FHIR, HL7, LLM evaluation frameworks, prompt or fine-tuning pipelines, safety controls, platformization, developer experience, open-source contributions, technical writing, or conference talks.
Benefits
- Employees work from the Bengaluru office at least three days per week, on Tuesday, Wednesday, and Friday.
- Some overlap with U.S. time zones is expected for customer and partner engagement.
- The role offers growth as a senior individual contributor or into technical leadership, with direct access to the founders.
Categories
