Senior Software Engineer, Agentic Platform - Moveworks
$161k - $274k • Mountain View, CALIFORNIA, United States • Full-time
Posted 7d ago
Job Location
Mountain View, CALIFORNIA, United States
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
We are seeking a Senior Software Engineer to join our Agentic Platform team. In this role, you will build and own the runtime infrastructure that powers Moveworks' AI agents, enabling them to orchestrate, execute, and deliver responses to millions of enterprise users in real time. This position is at the intersection of large language models and distributed systems, where you will leverage your expertise in machine learning, LLMs, and distributed systems to enhance agent planning, reasoning, and tool usage reliability at enterprise scale. Our AI agents are designed to handle complex workflows, including planning, multi-step execution, tool calling, and user interaction, all while ensuring correctness, observability, and low latency.
Responsibilities
- Develop and maintain the agent orchestration engine, a state machine managing long-running agent sessions and coordinating LLM calls and tool invocations.
- Implement model routing and adaptation strategies, including fine-tuning or distilling LLMs for specific agent tasks while meeting enterprise requirements.
- Build distributed session management systems using lease-based ownership, conditional writes, heartbeat protocols, and crash recovery via checkpointing.
- Design and operate an event-driven message pipeline for ordered delivery, event processing, and real-time streaming.
- Implement structured concurrency for managing multiple concurrent tasks per session with fail-fast semantics and graceful cancellation.
- Develop observability infrastructure using OpenTelemetry for distributed tracing and custom span lifecycle management.
- Create caching and state layers using Redis and DynamoDB for efficient data management and configuration.
- Build tool and agent connectivity for LLMs, including MCP and agent-to-agent capabilities, enabling LLMs to select and call the appropriate tools from large catalogs.
- Optimize token efficiency and context engineering to reduce agent costs and latency through prompt discipline, caching, and speculative/parallel model-call scheduling.
- Evaluate and adopt open-weights LLMs, benchmarking their performance on agent tasks to determine production readiness.
Requirements
- 5+ years of experience building production backend/infrastructure systems.
- Strong proficiency in Python or Go, ideally both.
- Experience designing and operating systems that handle significant real-time traffic.
- Hands-on experience building production systems that utilize LLMs or other ML models.
- Comfort with ambiguity and solving novel problems.
- Deep experience in at least three of the following areas: distributed systems (consistency models, idempotency, distributed locking), concurrent/async programming (Python asyncio, Go goroutines), event-driven architectures (message queues, pub/sub), database systems for infrastructure (DynamoDB, Redis), observability (OpenTelemetry, distributed tracing), gRPC/protobuf, or machine learning (LLMs, NLP, LLM evaluation).
Benefits
- Base pay of $161,300 - $274,200
- Equity (when applicable)
- Variable/incentive compensation
- Health plans, including flexible spending accounts
- 401(k) Plan with company match
- ESPP
- Matching donations
- Flexible time away plan
- Family leave programs
