We’re hiring at Pitney Bowes, where top talent builds meaningful careers and lasting impact. We Move fast, Deliver excellence, and Win together…that’s The Pitney Bowes way. Here, how we work matters just as much as what we achieve.
We’re looking for people who:
Act with urgency, accountability, and purpose
Deliver high quality work with consistency and pride
Collaborate effectively and elevate those around them
Focus on outcomes that drive impact and growth
Job Description:
Join Pitney Bowes as Advisory Software Engineer
Years of Experience: 6-8 years
Role: Fulltime(3 days/week in office)
Job Location: Pune/Noida
About the role
The AI CoE builds and ships agentic AI systems that sit on top of our core product APIs - a Copilot platform on Amazon Bedrock AgentCore, MCP-based tool servers, and AI advisors embedded in our shipping products. We are past the demo stage and into the part that is genuinely hard: making non-deterministic systems reliable, governed, measurable, and safe enough to put in front of customers and internal users.
This role owns the backlog and the delivery cadence for that work. You are the single throat to choke for what the team builds next and the reason the team can build it without friction. You will spend your day equally between defining outcomes with engineering, product, and security stakeholders - and clearing the path so the pod can actually deliver them.
This is a hands-on-the-details role, not a ceremony-running role. You will be expected to read an architecture diagram, argue about where the human-in-the-loop gate belongs, and write acceptance criteria for a system whose output is different every time you run it.
What you will own
Product ownership
Own and groom the backlog for one or more AI pods (agent platform, AI advisor products, or AI productivity tooling). Set sprint goals that ladder to quarterly outcomes, not activity.
Translate ambiguous executive intent ("we need an agent that helps SMBs ship smarter") into epics, stories, and acceptance criteria engineers can start on Monday.
Write acceptance criteria for probabilistic systems: define what "good" means for an agent response, what the eval set is, what the pass threshold is, and what the failure mode is when it misses.
Own the definition of done for agent capabilities - including evals, guardrails, observability, cost per interaction, and rollback path, not just "the happy path works."
Prioritize ruthlessly across competing stakeholders: product management, engineering leadership, security, architecture, and the business units consuming the platform.
Maintain the tool and capability catalog for the agent platform - which APIs are exposed as agent tools, which are approval-gated, which are read-only, and why.
Scrum mastery and delivery
Run sprint planning, standup, review, and retrospective for the pod. Keep them short and keep them useful.
Track and report delivery health: velocity, cycle time, spillover, blocked-time. Bring problems forward early rather than explaining them in hindsight.
Remove impediments - cross-team dependencies, environment access, security review queues, vendor bottlenecks. Escalate with a proposed resolution, not just a flag.
Facilitate estimation and scope negotiation in a domain where estimates are genuinely uncertain, without letting uncertainty become an excuse.
Coordinate across pods and with partner teams (platform engineering, data, security, product) so integration work is planned rather than discovered.
Technical stewardship
Partner with the architecture lead on target-state decisions and carry those decisions into the backlog with enough fidelity that they survive contact with implementation.
Maintain requirement traceability from product requirements through to delivered agent behavior, including where a requirement was deliberately descoped and why.
Own the AI governance checkpoints in the delivery flow: model approval, data handling review, human-in-the-loop placement, prompt and tool change control, and audit evidence.
Keep a live view of platform economics - token spend, model selection, inference cost per use case - and treat cost regressions as defects.
Run POCs as time-boxed experiments with a written decision at the end, not as open-ended projects.
What success looks like
First 90 days
You know the platform architecture well enough to explain it to a VP without an engineer in the room.
The backlog for your pod is groomed two sprints deep with acceptance criteria that engineers do not have to re-litigate in planning.
You have identified and closed the three largest sources of delivery friction for the pod.
By six months
Predictable delivery: sprint goals met consistently, spillover trending down, dependencies surfaced before they block.
Every shipped agent capability has an eval set, a guardrail spec, and a cost-per-interaction number attached to it.
Stakeholders across product, engineering, and security come to you for status rather than assembling it themselves.
What you will build
Agent runtime and orchestration - multi-agent systems on Bedrock AgentCore: routing, session and memory management, tool selection, retry and fallback behavior, and human-in-the-loop approval gates for actions that cost money.
MCP tool servers - clean, well-scoped tool interfaces over production APIs (address validation, rate shopping, label creation, tracking). Deciding what not to expose is as much of the job as building what you do.
Retrieval and grounding - ingestion pipelines, chunking and embedding strategy, vector and hybrid search, and freshness guarantees over documentation, contracts, and operational data.
Evaluation and guardrails - golden datasets, automated regression gates in CI, LLM-as-judge harnesses, input/output filtering, PII handling, and prompt-injection defenses on any tool that touches untrusted content.
Platform plumbing - auth and identity propagation across agent and tool layers, rate limiting, caching, cost and token instrumentation, tracing, and the dashboards that tell us when quality has quietly regressed.
What you will do
Design and ship production backend services in Python and/or Java on AWS, with the tests, observability, and runbooks that make them supportable at 2am.
Take an ambiguous capability ("the agent should recommend a cheaper carrier when SLA allows") and drive it to a designed, evaluated, instrumented, deployed feature.
Write and review architecture and design docs. Argue the trade-offs in writing before the code exists.
Build evals alongside features. A capability without a regression test is not done.
Own cost and latency as first-class engineering constraints - model selection, prompt size, caching, and parallelism are your levers.
Participate in code review, on-call rotation, and incident response. Write blameless postmortems.
Preferred qualifications
Hands-on exposure to a managed agent platform (Amazon Bedrock / AgentCore, Azure AI Foundry, Vertex AI Agent Builder) and to MCP or a comparable tool-integration protocol.
Experience defining evaluation frameworks for LLM systems - golden sets, LLM-as-judge, human review loops, regression gating.
Familiarity with enterprise data platforms (Snowflake or equivalent) and with data governance constraints on AI systems.
Experience operating inside an AI governance or model risk process in a regulated or enterprise environment.
Background in logistics, shipping, supply chain, or B2B SaaS.
CSPO, PSPO, CSM, PSM, or SAFe certification - useful, not a substitute for judgment.
Desired Competencies
5+ years in technical product ownership, technical program management, or engineering delivery leadership on software platforms - with at least 2 years directly accountable for a backlog.
Demonstrated experience delivering AI/ML or LLM-based features to production. Prototypes and pilots count only if you can describe what broke when real users arrived.
Working fluency with modern AI application patterns: prompting, RAG, tool/function calling, agent orchestration, evaluation, and guardrails. You do not need to write the code; you need to reason about the design.
Strong API literacy - you can read an OpenAPI spec, understand auth models, and reason about latency, idempotency, and error handling.
Proven Scrum or Kanban facilitation with distributed teams, including offshore or multi-timezone pods.
Excellent written communication. This role produces a lot of writing that executives read.
Comfort with ambiguity and with saying "not this sprint" to senior stakeholders.
The Team
Pitney Bowes (NYSE: PBI) is a global shipping and mailing company that provides technology, logistics, and financial services to more than 90 percent of the Fortune 500. Small business, retail, enterprise, and government clients around the world rely on Pitney Bowes to remove the complexity of sending mail and parcels. For additional information visit Pitney Bowes at www.pitneybowes.com.
We will:
Provide the will: opportunity to grow and develop your career- Offer an inclusive environment that encourages diverse perspectives and ideas
- Deliver challenging and unique opportunities to contribute to the success of a transforming organization
- Offer comprehensive benefits globally (PB Benefits and Wellbeing Programs)
Pitney Bowes is an equal opportunity employer that values diversity and inclusiveness in the workplace.
All interested individuals must apply online.
