Software Engineer, Distributed Systems & AI Agents (Senior Level)

At Instabase, we’re passionate about democratizing access to cutting-edge AI innovation to enable any organization to solve previously unsolvable unstructured data problems in their industry. With customers representing some of the largest and most complex organizations in the world, and investors like Greylock, Andreessen Horowitz, and Index Ventures, our market opportunity is near infinite.

Instabase offers a consumption-based pricing model where customers can pay only for what they use, aligning directly with the value our products deliver. It empowers our clients to explore our AI Hub platform features extensively, enabling them to uncover crucial business insights. This customer-centric model allows Instabase to glean insights from diverse use cases and behaviors, ensuring we deliver top-tier solutions that provide unmatched advantages for everyday business operations.

With offices in San Francisco and Bengaluru, Instabase is a truly global company. We are people-first , and we’ve built a fearlessly experimental, endlessly curious, customer obsessed team who work together and help organizations around the world turn their unstructured data into insights instantly.

The Role We are looking for a systems-minded engineer to build the distributed backend and execution infrastructure that powers AI agents. You will help build scalable, reliable, and secure systems at the intersection of distributed systems, agentic execution, and applied AI.

About The Team The team tackles some of the most challenging technical problems in scaling the capabilities and utility of agents and agentic models. Our work enables best-in-class platforms that leverage the world’s most capable models and maximize the value of agentic products for users across enterprises, small and medium-sized businesses, and individuals. We work across several interconnected areas:

• Distributed systems for processing large-scale unstructured-data extraction workloads.
• Reliable backend infrastructure for agentic execution and long-running AI workflows.
• R&D into advances in LLMs and AI, including benchmarks and new approaches to solving complex platform and customer problems.

What You Will Do

• Take new ideas from 0-to-1 quickly, then evolve their architecture to scale by orders of magnitude—from early prototypes to production systems handling workloads that are 10×, 1,000×, or even 1,000,000× larger.
• Build scalable distributed systems for large-scale unstructured-data extraction and agentic workloads.
• Develop reliable execution infrastructure for scheduling, retries, timeouts, cancellation, rate limits, and failure recovery.
• Build agent runtimes that coordinate model calls, tool execution, durable state, multi-step loops, and human approvals.
• Evaluate emerging models and AI techniques through benchmarks and experiments, and apply them to new platform and customer problems.
• Own systems from design through production, including testing, observability, and pragmatic trade-offs across reliability, performance, security, and cost.

About You

• 5+ years of software engineering experience building and operating production backend systems, with the ability and experience toserve as a technical lead—setting direction, leading teams through complex projects, and mentoring and coaching engineers while remaining hands-on.
• Strong fundamentals in distributed systems, concurrency, APIs, data modeling, and failure handling.
• Experience with agentic execution systems, workflow orchestration, event processing, scheduling, or high-volume services.
• Proficiency in a backend language such as Python, Go, Java, Kotlin, Rust, or C++.
• Experience with queues, databases, caching, containers, cloud infrastructure, and production observability.
• Experience building or integrating ML, generative-AI, or LLM-based systems, including tool calling and agent workflows.
• A strong ownership mindset across design, deployment, monitoring, incident response, and continuous improvement.

Helpful experience: workflow engines or task executors; Kafka, Temporal, Celery, Ray, or similar systems; Kubernetes; agent runtimes, RAG, evaluations, model gateways, MCP, or AI observability.

Instabase is an Equal Opportunity Employer. Qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender perception or identity, national origin, age, marital stat…