You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
ServiceNow

Senior Software Engineer, Agentic Platform - Moveworks

  • Office
  • 6+ years

Salary

$161,300 - 274,200/ year

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The team builds the runtime behind the company's AI agents: the layer that orchestrates agent work, executes it, and delivers responses to millions of enterprise users live.

The role combines large language models with distributed systems. You will use machine learning and LLM work to help agents plan, reason, and call tools dependably, and you will build the production infrastructure that runs them at enterprise scale.

Agents plan, run multi-step workflows, call tools, pause for a person, and pick up again, while staying correct, observable, and fast. You will design and own the systems that make this work.

Responsibilities

  • Build the agent orchestration engine, a state machine that tracks long-running sessions and coordinates planning, execution, and user exchanges across many LLM calls and tool runs.
  • Select, route between, and fine-tune or distill LLMs for each agent task, meeting enterprise needs such as fine-grained permissions, fresh data, explainability, and retained general knowledge.
  • Manage distributed sessions with lease-based ownership through conditional writes, heartbeats, and checkpoint-based crash recovery.
  • Build the event pipeline: FIFO queues for ordered delivery, event consumers, and real-time streaming over gRPC and Socket.IO.
  • Run several concurrent tasks per session with structured concurrency, fail-fast behavior, and clean cancellation.
  • Build observability with OpenTelemetry, trace context across async boundaries, and custom span handling for sessions that last minutes.
  • Build caching and state layers on Redis and DynamoDB key-value stores scoped per org and per bot, with batch reads and hot-reloaded configuration.
  • Build MCP and agent-to-agent (A2A) connectivity, including tool discovery, namespacing, and selection across large catalogs so the LLM picks the right tool from thousands of options.
  • Cut agent cost and latency through prompt and context discipline, caching, speculative and parallel model-call scheduling, and fewer tokens across multi-step reasoning chains.
  • Quickly stand up newly released open-weights LLMs at several quantization levels, benchmark accuracy, latency, and cost on agent tasks, and decide which models move to production.

Requirements

  • At least 3 of the following areas, with deep experience in those 3.
  • Distributed systems: consistency models, idempotency, exactly-once delivery, distributed locking and leasing.
  • Concurrent and async programming: Python asyncio, Go goroutines, structured concurrency, cancellation handling.
  • Event-driven architectures: message queues such as SQS and Kafka, pub/sub, backpressure, delivery guarantees.
  • Database systems for infrastructure: DynamoDB conditional writes and transactions, Redis connection pooling and pub/sub.
  • Observability: OpenTelemetry, distributed tracing, span context propagation, Prometheus metrics.
  • gRPC and 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 or infrastructure systems.
  • Required: strong in Python or Go, ideally both.
  • Required: experience designing and operating systems that handle real traffic at scale.
  • Required: hands-on experience building production systems that use LLMs or other ML models.
  • Required: comfort working through ambiguity on novel problems without textbook answers.
  • Relevant past experience: building and shipping products on LLMs using techniques such as RAG, chain-of-thought, self-reflection, tool and function calling, and agentic reasoning.
  • Relevant past experience: training, fine-tuning, or evaluating ML models on large datasets in production, especially for NLP, retrieval, or ranking.
  • Relevant past experience: improving relevance or quality through experiments, including designing metrics, building evaluation datasets, and developing ranking or model-selection signals.
  • Relevant past experience: research or applied work in machine learning, LLMs, agentic systems, information retrieval, or ranking and relevance.

Conditions

For positions in this location, base pay is $161,300 - $274,200, a guideline that varies with qualifications, skill level, competencies, and work location, plus equity where applicable and variable or incentive pay.

Pay depends on the geographic location of the role and may change with work location.

Sales positions generally offer an On Target Earnings (OTE) incentive structure.

Work persona is flexible, remote, or required in office, assigned based on the nature of the work and the assigned work location.

To confirm eligibility for a work persona, the company may measure the distance from your main residence to its nearest office using a third-party service.

Benefits

  • Health plans, including flexible spending accounts.
  • 401(k) plan with company match.
  • Employee stock purchase plan (ESPP).
  • Matching donations.
  • Flexible time-away plan.
  • Family leave programs.

Where you’d work

From the office

The office

About the company

ServiceNow

  • Industry: SaaS

Office in Mountain View, United States

Also hiring in United States, San Diego, United States, Frankfurt, Germany and 13 more places

71 of their 207 open roles are remote

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 21 checks run
  • 1 red flag

Still hiring?

14 checks

1 red flag

How crowded?

7 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details13 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • Python
  • Go
  • AWS
  • Kafka
  • Prometheus
  • gRPC
  • Redis
  • LLMs
  • RAG
Seniority
Senior
Type
Full-time
Equity
Equity offered
Industry
SaaS
Specialty
Backend
Show 7 more factsShow less

Role

Category
Development
Specialty
Backend
Seniority
Senior
Experience
5+ years
Tech stack
  • Python
  • Go
  • AWS
  • Kafka
  • Prometheus
  • gRPC
  • Redis
  • LLMs
  • RAG

Location

Work model
Office
Region
United States
Office
  • Mountain View, United States

Compensation

Salary
$161,300 - 274,200 / year
Pay period
Annual
Equity
Equity offered

Employment

Type
Full-time

Company

Industry
SaaS

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason