Senior Software Engineer

Description

We're building the runtime infrastructure that powers Moveworks' AI agents — the systems that orchestrate, execute, and deliver agent responses to millions of enterprise users in real time. This role sits where large language models meet distributed systems. You'll apply machine learning, LLM, and distributed systems expertise to make agents plan, reason, and use tools reliably, and you'll build the production systems that run those agents at enterprise scale.

Our AI agents can plan, execute multi-step workflows, call tools, wait on human input, and resume — all while maintaining correctness, observability, and low latency. The systems that make this possible are what you'll build and own.

What you get to do in this role:

Agent orchestration engine — A state machine that manages long-running agent sessions, coordinating planning, execution, and user interaction across multiple LLM calls and tool invocations

Model routing and adaptation — Choose, route between, and fine-tune or distill LLMs for specific agent tasks. Meet enterprise requirements such as granular permissions, data freshness, explainability, and preserving general knowledge.

Distributed session management — Lease-based ownership using conditional writes, heartbeat protocols, and crash recovery via checkpointing

Event-driven message pipeline — FIFO queues for ordered delivery, consumers for event processing, and real-time streaming via gRPC and Socket.IO

Structured concurrency — Running multiple concurrent tasks per session with fail-fast semantics and graceful cancellation

Observability infrastructure — OpenTelemetry instrumentation, distributed trace context propagation across async boundaries, custom span lifecycle management for sessions that span minutes

Caching and state layers — Redis, DynamoDB KV stores with per-org/per-bot scoping, batch read optimization, and hot-reload configuration

Tool and agent connectivity for LLMs: Build MCP and agent-to-agent (A2A) capabilities, including tool discovery, namespacing, and tool selection over large tool catalogs, so the LLM picks and calls the right tool from thousands of candidates.

Token efficiency and context engineering — Lower the agent's cost and latency through prompt and context discipline, caching, speculative and parallel model-call scheduling, and reducing tokens spent across multi-step LLM reasoning chains.

Open-weights model adoption and evaluation — Quickly stand up newly released open-weights LLMs at different quantization levels, run them in a test environment, and benchmark their accuracy, latency and cost on agent tasks. Use the results to decide which models reach production.

Responsibilities

• We're building the runtime infrastructure that powers Moveworks' AI agents — the systems that orchestrate, execute, and deliver agent responses to millions of enterprise users in real time. This role sits where large language models meet distributed systems. You'll apply machine learning, LLM, and distributed systems expertise to make agents plan, reason, and use tools reliably, and you'll build the production systems that run those agents at enterprise scale.
• Our AI agents can plan, execute multi-step workflows, call tools, wait on human input, and resume — all while maintaining correctness, observability, and low latency. The systems that make this possible are what you'll build and own.
• What you get to do in this role:
• Agent orchestration engine — A state machine that manages long-running agent sessions, coordinating planning, execution, and user interaction across multiple LLM calls and tool invocations
• Model routing and adaptation — Choose, route between, and fine-tune or distill LLMs for specific agent tasks. Meet enterprise requirements such as granular permissions, data freshness, explainability, and preserving general knowledge.
• Distributed session management — Lease-based ownership using conditional writes, heartbeat protocols, and crash recovery via checkpointing
• Event-driven message pipeline — FIFO queues for ordered delivery, consumers for event processing, and real-time streaming via gRPC and Socket.IO
• Structured concurrency — Running multiple concurrent tasks per session with fail-fast semantics and graceful cancellation
• Observability infrastructure — OpenTelemetry instrumentation, distributed trace context propagation across async boundaries, custom span lifecycle management for sessions that span minutes
• Caching and state layers — Redis, DynamoDB KV stores with per-org/per-bot scoping, batch read optimization, and hot-reload configuration
• Tool and agent connectivity for LLMs: Build MCP and agent-to-agent (A2A) capabilities, including tool discovery, namespacing, and tool selection over large tool catalogs, so the LLM picks and calls the right tool from thousands of candidates.
• Token efficiency and context engineering — Lower the agent's cost and latency through prompt and context discipline, caching, speculative and parallel model-call scheduling, and reducing tokens spent across multi-step LLM reasoning chains.
• Open-weights model adoption and evaluation — Quickly stand up newly released open-weights LLMs at different quantization levels, run them in a test environment, and benchmark their accuracy, latency and cost on agent tasks. Use the results to decide which models reach production.

Requirements

• To be successful in this role you have:
• You should have deep experience in at least 3 of these areas:
• Distributed systems: consistency models, idempotency, exactly-once delivery, distributed locking/leasing
• Concurrent/async programming: Python asyncio, Go goroutines, structured concurrency, cancellation handling
• Event-driven architectures: message queues (SQS, Kafka), pub/sub, backpressure, delivery guarantees
• Database systems for infrastructure: DynamoDB (conditional writes, transactions), Redis (connection pooling, pub/sub)
• Observability: OpenTelemetry, distributed tracing, span context propagation, Prometheus metrics
• gRPC/protobuf: streaming RPCs, service interface design, error handling patterns
• Machine learning: Large language models, natural language processing, LLM evaluation
• Required:
• 5+ years building production backend/infrastructure systems
• Strong in Python or Go (ideally both)
• Experience designing and operating systems that handle real traffic at scale
• Hands-on experience building production systems that use LLMs or other ML models
• Comfort with ambiguity — these are novel problems without textbook solutions
• Relevant past experience:
• Building and shipping products on large language models with techniques such as RAG, chain-of-thought, self-reflection, tool and function calling, and agentic reasoning.
• Training, fine-tuning, or evaluating machine learning models on large datasets in production, especially for NLP, retrieval, or ranking.
• Improving relevance or quality through careful experimentation: designing metrics, building evaluation datasets, and developing new features and signals for ranking or model selection.
• Research or applied work in machine learning, LLMs, agentic systems, information retrieval, or ranking and relevance.
• Additional Information
• Work Personas
• We approach our distributed world of work with flexibility and trust. Work personas (flexible, remote, or required in office) are categories that are assigned to the company employees depending on the nature of their work and their assigned work location. Learn more here . To determine eligibility for a work persona, the company may confirm the distance between your primary residence and the closest the company office using a third-party service.